claimcheck-rules / rules /dates.json
NagaYu's picture
ClaimCheck v1.1.0: rule pack, policy presets and 158-case bilingual evaluation set
e518d03 verified
Raw History Blame Contribute Delete
2.75 kB
{
"rules_version": "1.1.0",
"description": "Date recognition and ISO normalisation.",
"patterns": [
"(?:令和|平成|昭和|大正|明治)\\s*(?:\\d{1,2}|元)\\s*年(?:\\s*\\d{1,2}\\s*月(?:\\s*\\d{1,2}\\s*日)?)?",
"\\d{4}\\s*年\\s*\\d{1,2}\\s*月\\s*\\d{1,2}\\s*日",
"\\d{4}\\s*年\\s*\\d{1,2}\\s*月",
"(?<![0-9A-Za-z])\\d{4}[-/.]\\d{1,2}[-/.]\\d{1,2}(?![0-9A-Za-z])",
"(?<![0-9A-Za-z])\\d{4}[-/]\\d{1,2}(?![-/.\\d])",
"(?<![0-9A-Za-z])(?:Jan|January|Feb|February|Mar|March|Apr|April|May|Jun|June|Jul|July|Aug|August|Sep|Sept|September|Oct|October|Nov|November|Dec|December)\\.?\\s+\\d{1,2}(?:st|nd|rd|th)?,?\\s+\\d{4}(?![0-9A-Za-z])",
"(?<![0-9A-Za-z])\\d{1,2}(?:st|nd|rd|th)?\\s+(?:Jan|January|Feb|February|Mar|March|Apr|April|May|Jun|June|Jul|July|Aug|August|Sep|Sept|September|Oct|October|Nov|November|Dec|December)\\.?,?\\s+\\d{4}(?![0-9A-Za-z])",
"(?<![0-9A-Za-z])(?:Jan|January|Feb|February|Mar|March|Apr|April|May|Jun|June|Jul|July|Aug|August|Sep|Sept|September|Oct|October|Nov|November|Dec|December)\\.?,?\\s+\\d{4}(?![0-9A-Za-z])",
"(?<![0-9A-Za-z])(?:FY)\\s?\\d{4}(?![0-9A-Za-z])",
"\\d{4}\\s*年度",
"(?<![0-9])\\d{4}\\s*年(?![0-9度])"
],
"relative_date_pattern": "(?:昨年|一昨年|来年|再来年|今年|本年|先月|今月|来月|先週|今週|来週|昨日|本日|今日|明日|明後日|現在|最近|近年|直近|先般|過去\\d+年|今後\\d+年|\\byesterday\\b|\\btoday\\b|\\btomorrow\\b|\\blast\\s+(?:year|month|week|quarter)\\b|\\bnext\\s+(?:year|month|week|quarter)\\b|\\bthis\\s+(?:year|month|week|quarter)\\b|\\brecently\\b|\\bcurrently\\b|\\bnowadays\\b)",
"era_offsets": {
"令和": 2018,
"reiwa": 2018,
"平成": 1988,
"heisei": 1988,
"昭和": 1925,
"showa": 1925,
"大正": 1911,
"taisho": 1911,
"明治": 1867,
"meiji": 1867
},
"month_names": {
"jan": 1,
"january": 1,
"feb": 2,
"february": 2,
"mar": 3,
"march": 3,
"apr": 4,
"april": 4,
"may": 5,
"jun": 6,
"june": 6,
"jul": 7,
"july": 7,
"aug": 8,
"august": 8,
"sep": 9,
"sept": 9,
"september": 9,
"oct": 10,
"october": 10,
"nov": 11,
"november": 11,
"dec": 12,
"december": 12
},
"notes": [
"Output granularity is preserved: YYYY, YYYY-MM or YYYY-MM-DD.",
"Era year N maps to offset + N, so 令和1 == 2019.",
"Relative expressions are counted but never become claims.",
"Word boundaries are NOT \\\\b: in 契約は2024-01-05に both sides are word characters, so \\\\b never fires and the date was invisible.",
"FY2024 and 2024年度 both normalise to 2024. Fiscal-year start months differ by country: a known false positive."
]
}