Last active
October 30, 2017 04:53
-
-
Save WaxCylinderRevival/677233e2baae9a5e414d57b8cdc2ed08 to your computer and use it in GitHub Desktop.
analyze-text-for-date-patterns.xq
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
(: declare namespace dp='https://history.state.gov/ns/xquery/date-processing' :) | |
declare variable $local:regexes := | |
map { | |
"month-regex" : "(?:January|February|March|April|May|June|July|August|September|October|November|December)", | |
"month-regex-fr" : "(?:janvier|février|fevrier|mart|avril|mai|juin|juillet|août|aout|septembre|octobre|novembre|décembre|decembre)", | |
"month-regex-sp" : "(?:enero|febrero|marzo|abril|mayo|junio|julio|agosto|septiembre|setiembre|octubre|noviembre|diciembre)", | |
"day-regex" : "(?:\d{1,2})(?:st|d|nd|rd|th)?", | |
"day-range-regex" : "(?:\d{1,2})(?:st|d|nd|rd|th)?\s*[-–—]\s*(?:\d{1,2})(?:st|d|nd|rd|th)?", | |
"year-regex" : "(?:\d{4})", | |
"day-spelled-out-regex" : "(?:(?:\d{1,2})(?:st|d|nd|rd|th)?|(?:thirtieth|thirty|twentieth|twenty)?(?:-|–|\s+)?(?:nineteenth|eighteenth|seventeenth|sixteenth|fifteenth|fourteenth|thirteenth|twelfth|eleventh|tenth|ninth|eighth|seventh|sixth|fifth|fourth|third|second|first)?)", | |
"year-spelled-out-regex" : "one\s+thousand\s+(?:nine|eight)\s+hundred\s+(?:ninety|eighty|seventy|sixty|fifty|forty|thirty|twenty)?(?:-\s+)?(?:nineteen|eighteen|seventeen|sixteen|fifteen|fourteen|thirteen|twelve|eleven|ten|nine|eight|seven|six|five|four|three|two|one)?" | |
} | |
; | |
declare function local:get-dates($source) { | |
let $day-month-year-regex := $local:regexes?day-regex || '\s+' || $local:regexes?month-regex || ',?\s+' || $local:regexes?year-regex | |
let $month-day-year-regex := $local:regexes?month-regex || '\s+' || $local:regexes?day-regex || ',?\s+' || $local:regexes?year-regex | |
let $month-day-range-year-regex := $local:regexes?month-regex || '\s+' || $local:regexes?day-range-regex || ',?\s+' || $local:regexes?year-regex | |
let $day-month-year-official-regex := $local:regexes?day-spelled-out-regex || '\s+day\s+of\s+' || $local:regexes?month-regex || ',\s+in\s+the\s+year\s+of\s+(?:our|the)\s+lord\s+' || $local:regexes?year-spelled-out-regex | |
let $day-month-year-regex-fr := $local:regexes?day-regex || '\s+' || $local:regexes?month-regex-fr || ',?\s+' || $local:regexes?year-regex | |
let $day-month-year-regex-sp := $local:regexes?day-regex || '\s+(?:de\s+)?' || $local:regexes?month-regex-sp || ',?\s+(?:(?:de|del)\s+)?' || $local:regexes?year-regex | |
return | |
( | |
analyze-string($source, $month-day-year-regex, "i"), | |
analyze-string($source, $month-day-range-year-regex, "i"), | |
analyze-string($source, $day-month-year-regex, "i"), | |
analyze-string($source, $day-month-year-official-regex, 'i'), | |
analyze-string($source, $day-month-year-regex-fr, "i"), | |
analyze-string($source, $day-month-year-regex-sp, "i") | |
) | |
}; |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Results: