private static string GetPattern(EnumLanguage language = EnumLanguage.NONE)
{
string pattern = "";
switch (language)
{
default:
{
// circa late eighth to early ninth century AD
pattern = String.Concat(
START,
maybe(DateCirca.Pattern(language) + SPACE),
maybe(oneof(Lookup <EnumDatePrefix> .Patterns(language), "prefix1") + SPACE),
oneof(Lookup <EnumOrdinal> .Patterns(language), "centuryMin"),
maybe(SPACE + "century"),
@"\s*(?:[e\;\-\/]|to|or)\s*",
maybe(oneof(Lookup <EnumDatePrefix> .Patterns(language), "prefix2") + SPACE),
oneof(Lookup <EnumOrdinal> .Patterns(language), "centuryMax"),
maybe(SPACE + "century"),
maybe(SPACE + oneof(Lookup <EnumDateSuffix> .Patterns(language), "suffix")),
END
);
break;
}
}
return(pattern);
}
private static string GetPattern(EnumLanguage language = EnumLanguage.NONE)
{
string pattern = "";
switch (language)
{
case EnumLanguage.IT:
{
// ^(?:(?:dal?|in|nel)\s)?(?:(?:C(?:\.|irca)|Intorno al)\s)?(?<year>\d+)(?:(?<suffix>a\.?C\.?|d\.?C\.?|B\.?P\.?|C\.?E\.?))?$
pattern = String.Concat(
START, // ^
maybe(oneof(new string[] { @"dal?", "in", "nel" }) + SPACE), // (?:(?:dal?|in|nel)\s)?
maybe(DateCirca.Pattern(language) + SPACE), // (?:(?:C(?:\.|irca)|Intorno al)\s)?
group(@"\d+", "year"), // (?<year>\d+)
maybe(SPACE), // (?:\s)?
maybe(oneof(Lookup <EnumDateSuffix> .Patterns(language), "suffix")), // (?:(?<suffix>a\.?C\.?|d\.?C\.?|B\.?P\.?|C\.?E\.?))?
END // $
);
break;
}
default:
{
// ^(?:(?:C(?:\.|irca)|around|approx(?:\.|imately)?)\s)?(?<year>\d+)(?:(?<suffix>B\.?C\.?|A\.?D\.?|B\.?P\.?|C\.?E\.?)\s)?$
pattern = String.Concat(
START, // ^
maybe(DateCirca.Pattern(language)), // (?:C(?:\.|irca)|around|approx(?:\.|imately)?)?
maybe(SPACE), // (?:\s)?
oneof(new string[] {
group(@"[+-]?\d+", "year"),
String.Concat(
group(@"\d+", "year"), // (?<year>\d+)
maybe(oneof(new string[] { @"\+", @"\?" })), // approximation indicator
maybe(SPACE), // (?:\s)?
maybe(oneof(Lookup <EnumDateSuffix> .Patterns(language), "suffix")) // (?<suffix>B\.?C\.?|A\.?D\.?|B\.?P\.?|C\.?E\.?)?
),
String.Concat(
maybe(oneof(Lookup <EnumDateSuffix> .Patterns(language), "suffix")), // (?<suffix>B\.?C\.?|A\.?D\.?|B\.?P\.?|C\.?E\.?)?
maybe(SPACE), // (?:\s)?
group(@"\d+", "year"), // (?<year>\d+)
maybe(oneof(new string[] { @"\+", @"\?" }))
)
}),
END // $
);
break;
}
}
return(pattern);
}
private static string GetPattern(EnumLanguage language = EnumLanguage.NONE)
{
string pattern = String.Concat(
START,
maybe(DateCirca.Pattern(language) + SPACE),
oneof(Lookup <EnumMonth> .Patterns(language), "month"),
//Month.Pattern(language, "month"),
SPACE,
group(@"\d+", "year"),
maybe(SPACE),
maybe(oneof(Lookup <EnumDateSuffix> .Patterns(language), "suffix")),
END
);
return(pattern);
}
private static string GetPattern(EnumLanguage language = EnumLanguage.NONE)
{
string[] patterns =
{
String.Concat(
START,
maybe(DateCirca.Pattern(language) + SPACE),
group(@"[+-]?\d+", "year"),
@"\s*\±\s*",
group(@"\d+", "tolerance"),
END
),
String.Concat(
START,
maybe(DateCirca.Pattern(language) + SPACE),
group(@"[+-]?\d+", "year"),
maybe(SPACE),
group(@"[+-]\d+", "tolerance1"),
maybe(SPACE),
group(@"[+-]\d+", "tolerance2"),
END
),
String.Concat(
START,
maybe(DateCirca.Pattern(language) + SPACE),
group(@"[+-]?\d+", "year"),
maybe(SPACE),
group(@"[+-]\d+", "tolerance"),
END
)
// @"^(?:c(?:irca|\.|)\s)?(?<year>\d+)\s*\±\s*(?<tolerance>\d+)$",
// @"^(?:c(?:irca|\.|)\s)?(?<year>\d+)\s*(?<tolerance>[+-]\d+)$",
// @"^(?:c(?:irca|\.|)\s)?(?<year>\d+)\s*(?<tolerance1>[+-]\d+)\s*(?<tolerance2>[+-]\d+)$"
};
return(oneof(patterns)); // (?:pattern1|pattern2|pattern3)
}
public static IYearSpan Match(string input, EnumLanguage language = EnumLanguage.NONE)
{
string pattern;
Match m;
// look for plusminus symbol tolerance pattern e.g. "1540±9" => { min: 1540, max: 1549, label: "1540+9" }
// pattern = @"^(?:c(?:irca|\.|)\s)?(?<year>\d+)\s*\±\s*(?<tolerance>\d+)$";
pattern = String.Concat(
START,
maybe(DateCirca.Pattern(language) + SPACE),
group(@"[+-]?\d+", "year"),
@"\s*\±\s*",
group(@"\d+", "tolerance"),
END
);
m = Regex.Match(input.Trim(), pattern, options);
if (m.Success)
{
int year = 0;
int tolerance = 0;
int.TryParse(m.Groups["year"].Value, out year);
int.TryParse(m.Groups["tolerance"].Value, out tolerance);
return(new YearSpan(year - tolerance, year + tolerance, input, "RxYearWithTolerance(1)"));
}
// look for plus minus tolerance pattern e.g. "1540+9-5" => { min: 1535, max: 1549, label: "1540+9-5" }
//pattern = @"^(?:c(?:irca|\.|)\s)?(?<year>\d+)\s*(?<tolerance1>[+-]\d+)\s*(?<tolerance2>[+-]\d+)$";
pattern = String.Concat(
START,
maybe(DateCirca.Pattern(language) + SPACE),
group(@"[+-]?\d+", "year"),
maybe(SPACE),
group(@"[+-]\d+", "tolerance1"),
maybe(SPACE),
group(@"[+-]\d+", "tolerance2"),
END
);
m = Regex.Match(input.Trim(), pattern, options);
if (m.Success)
{
int year = 0;
int tolerance1 = 0;
int tolerance2 = 0;
int.TryParse(m.Groups["year"].Value, out year);
int.TryParse(m.Groups["tolerance1"].Value, out tolerance1);
int.TryParse(m.Groups["tolerance2"].Value, out tolerance2);
return(new YearSpan(year + tolerance1, year + tolerance2, input, "RxYearWithTolerance(2)"));
}
// look for single tolerance pattern e.g. "1540+9" => { min: 1540, max: 1549, label: "1540+9" }
//pattern = @"^(?:c(?:irca|\.|)\s)?(?<year>\d+)\s*(?<tolerance>[+-]\d+)$";
pattern = String.Concat(
START,
maybe(DateCirca.Pattern(language) + SPACE),
group(@"\d+", "year"),
maybe(SPACE),
group(@"[+-]\d+", "tolerance"),
END
);
m = Regex.Match(input.Trim(), pattern, options);
if (m.Success)
{
int year = 0;
int tolerance = 0;
int.TryParse(m.Groups["year"].Value, out year);
int.TryParse(m.Groups["tolerance"].Value, out tolerance);
return(new YearSpan(year, year + tolerance, input, "RxYearWithTolerance(3)"));
}
// if we reach here nothing matched
return(null);
}
private static string GetPattern(EnumLanguage language = EnumLanguage.NONE)
{
string pattern = "";
switch (language)
{
case EnumLanguage.IT:
{
// ^(?:(?:Intorno\sal|circa)\s)?(?<yearMin>\d{3,})(?:\s*[;\-\/]\s*)(?<yearMax>\d{2,})\s*(?<suffix>a\.?C\.?|d\.?C\.?)?$
pattern = String.Concat(
START, // ^
maybe(oneof(new string[] { "tra lo", "in" }) + SPACE), // (?:(?:tra lo|in)\s)?
maybe(DateCirca.Pattern(language) + SPACE), // (?:(?:Intorno\sal|circa)\s)?
oneof(new string[] {
String.Concat(
maybe(oneof(Lookup <EnumDateSuffix> .Patterns(language), "suffix1")),
maybe(SPACE),
group(@"\d+", "yearMin")
),
String.Concat(
group(@"\d+", "yearMin"),
maybe(SPACE),
maybe(oneof(Lookup <EnumDateSuffix> .Patterns(language), "suffix1"))
)
}),
oneof(new string[] { @"\s*[\;\-\/]\s*", @"\sed?\slo\s" }), // separator
oneof(new string[] {
String.Concat(
maybe(oneof(Lookup <EnumDateSuffix> .Patterns(language), "suffix2")),
maybe(SPACE),
group(@"\d+", "yearMax")
),
String.Concat(
group(@"\d+", "yearMax"),
maybe(SPACE),
maybe(oneof(Lookup <EnumDateSuffix> .Patterns(language), "suffix2"))
)
}),
END // $
);
break;
}
case EnumLanguage.NL:
{
pattern = String.Concat(
START,
maybe(@"tussen" + SPACE), // "between"
maybe(DateCirca.Pattern(language) + maybe(SPACE)),
group(@"\d+", "yearMin"),
maybe(SPACE),
maybe(oneof(Lookup <EnumDateSuffix> .Patterns(language), "suffix1")),
@"\s*(?:[\;\-\/]|en)\s*", // separators
maybe(DateCirca.Pattern(language) + maybe(SPACE)),
group(@"\d+", "yearMax"),
maybe(SPACE),
maybe(oneof(Lookup <EnumDateSuffix> .Patterns(language), "suffix2")),
END
);
break;
}
default:
{
// ^(?:c(?:\.|irca)?)?\s*(?<yearMin>\d+)(?:\s*(?:[;\-\/]|to)\s*)(?<yearMax>\d+)\s*(?<suffix>AD|BC|CE|BP)?\s*\??$
pattern = String.Concat(
START,
maybe(DateCirca.Pattern(language) + maybe(SPACE)),
oneof(new string[] {
group(@"[+-]?\d+", "yearMin"),
String.Concat(
maybe(oneof(Lookup <EnumDateSuffix> .Patterns(language), "suffix1")),
maybe(SPACE),
group(@"\d+", "yearMin")
),
String.Concat(
group(@"\d+", "yearMin"),
maybe(SPACE),
maybe(oneof(Lookup <EnumDateSuffix> .Patterns(language), "suffix1"))
)
}),
@"\s*(?:[\;\-\/]|to)\s*", // separators
oneof(new string[] {
group(@"[+-]?\d+", "yearMax"),
String.Concat(
maybe(oneof(Lookup <EnumDateSuffix> .Patterns(language), "suffix2")),
maybe(SPACE),
group(@"\d+", "yearMax")
),
String.Concat(
group(@"\d+", "yearMax"),
maybe(SPACE),
maybe(oneof(Lookup <EnumDateSuffix> .Patterns(language), "suffix2"))
)
}),
END
);
break;
}
}
return(pattern);
}
// done like this so they are only read once
/* private static Lazy<IList<Ordinal>> _ordinals = new Lazy<IList<Ordinal>>(() => getOrdinals(), true);
* private static IList<Ordinal> ordinals
* {
* get
* {
* return _ordinals.Value;
* }
* }
* private static IList<Ordinal> getOrdinals()
* {
* IList<Ordinal> ordinals = null;
* string path = "";
* if (System.Web.HttpContext.Current != null)
* path = System.Web.HttpContext.Current.Request.MapPath("~\\ordinals.json");
* else
* path = "ordinals.json"; // tests don't have HttpContext, so were failing
* ordinals = Newtonsoft.Json.JsonConvert.DeserializeObject<IList<Ordinal>>(System.IO.File.ReadAllText(path));
* return ordinals;
* }
*/
// attempt to get a match on ordinal
/*protected int getOrdinalNoFromName(string name, EnumLanguage language)
* {
* IOrdinal match = null;
* match = ordinals.FirstOrDefault(o => o.label == name.Trim().ToLower() && (language != EnumLanguage.NONE ? o.language == language : true));
* return (match == null ? 0 : match.value);
* } */
private static string GetPattern(EnumLanguage language = EnumLanguage.NONE)
{
string pattern = "";
switch (language)
{
case EnumLanguage.CY:
pattern = String.Concat(
START,
maybe(DateCirca.Pattern(language) + SPACE),
maybe(oneof(Lookup <EnumDatePrefix> .Patterns(language), "prefix") + SPACE),
oneof(Lookup <EnumOrdinal> .Patterns(language), "ordinal"),
SPACE,
@"[cg]anrif",
maybe(SPACE + oneof(Lookup <EnumDateSuffix> .Patterns(language), "suffix")),
END
);
break;
case EnumLanguage.FR:
pattern = String.Concat(
START,
maybe(DateCirca.Pattern(language) + SPACE),
maybe(oneof(Lookup <EnumDatePrefix> .Patterns(language), "prefix") + SPACE),
oneof(Lookup <EnumOrdinal> .Patterns(language), "ordinal"),
SPACE,
@"s(?:\.|iècle)",
maybe(SPACE + oneof(Lookup <EnumDateSuffix> .Patterns(language), "suffix")),
END
);
break;
case EnumLanguage.IT:
pattern = String.Concat(
START, // ^
maybe(DateCirca.Pattern(language) + SPACE), // (?:(?:C(?:\.|irca)|Intorno al)\s)?
maybe(oneof(Lookup <EnumDatePrefix> .Patterns(language), "prefix") + SPACE),
oneof(new string[] {
@"sec(?:\.|olo)" + SPACE + oneof(Lookup <EnumOrdinal> .Patterns(language), "ordinal"),
oneof(Lookup <EnumOrdinal> .Patterns(language), "ordinal") + SPACE + @"sec(?:\.|olo)"
}),
maybe(SPACE + oneof(Lookup <EnumDateSuffix> .Patterns(language), "suffix")), // (?:\s(?<suffix>a\.?C\.?|d\.?C\.?))?
END // $
);
break;
case EnumLanguage.NL:
pattern = String.Concat(
START,
maybe(DateCirca.Pattern(language) + SPACE),
maybe(oneof(Lookup <EnumDatePrefix> .Patterns(language), "prefix") + SPACE),
oneof(Lookup <EnumOrdinal> .Patterns(language), "ordinal"),
SPACE,
@"eeuw",
maybe(SPACE + oneof(Lookup <EnumDateSuffix> .Patterns(language), "suffix")),
END
);
break;
case EnumLanguage.SV:
pattern = String.Concat(
START,
maybe(DateCirca.Pattern(language) + SPACE),
maybe(oneof(Lookup <EnumDatePrefix> .Patterns(language), "prefix") + SPACE),
oneof(Lookup <EnumOrdinal> .Patterns(language), "ordinal"),
SPACE,
@"århundrade",
maybe(SPACE + oneof(Lookup <EnumDateSuffix> .Patterns(language), "suffix")),
END
);
break;
default:
pattern = String.Concat(
START, // ^
maybe(DateCirca.Pattern(language) + SPACE),
maybe(oneof(Lookup <EnumDatePrefix> .Patterns(language), "prefix") + SPACE), // (?:
oneof(Lookup <EnumOrdinal> .Patterns(language), "ordinal"),
SPACE,
@"centur(?:y|ies)",
maybe(SPACE + oneof(Lookup <EnumDateSuffix> .Patterns(language), "suffix")),
END
);
break;
}
return(pattern);
}
private static string GetPattern(EnumLanguage language = EnumLanguage.NONE)
{
string pattern = "";
switch (language)
{
case EnumLanguage.CY:
{
pattern = String.Concat(
START,
maybe(DateCirca.Pattern(language) + SPACE),
maybe(oneof(Lookup <EnumDatePrefix> .Patterns(language), "prefix1") + SPACE),
group(@"\d+", "centuryMin"),
oneof(new string[] { "af", "a?il", "ydd", "f?ed", "eg", "ain" }),
maybe(SPACE + "ganrif"),
@"\s*[\s\;\-\/]\s*",
maybe(oneof(Lookup <EnumDatePrefix> .Patterns(language), "prefix2") + SPACE),
group(@"\d+", "centuryMax"),
oneof(new string[] { "af", "a?il", "ydd", "f?ed", "eg", "ain" }),
SPACE,
"ganrif",
maybe(SPACE + oneof(Lookup <EnumDateSuffix> .Patterns(language), "suffix")),
END
);
break;
}
case EnumLanguage.FR:
{
pattern = String.Concat(
START,
maybe(DateCirca.Pattern(language) + SPACE),
maybe(oneof(Lookup <EnumDatePrefix> .Patterns(language), "prefix1") + SPACE),
group(ROMAN, "centuryMin"), // (?<centuryMin>[MCDLXVI]+)
oneof(new string[] { "è?[mr]e", "er", "re", "[eè]", "n?de?", "o" }),
maybe(SPACE + @"s(?:\.|iècle)"),
@"\s*[\;\-\/]\s*", // separators
maybe(oneof(Lookup <EnumDatePrefix> .Patterns(language), "prefix2") + SPACE),
group(ROMAN, "centuryMax"), // (?<centuryMax>[MCDLXVI]+)
oneof(new string[] { "è?[mr]e", "er", "re", "[eè]", "n?de?", "o" }),
maybe(SPACE + @"s(?:\.|iècle)"),
maybe(SPACE + oneof(Lookup <EnumDateSuffix> .Patterns(language), "suffix")), // (?:\s(?<suffix>a\.?C\.?|d\.?C\.?))?
END
);
break;
}
case EnumLanguage.IT:
{
pattern = String.Concat(
START,
maybe(@"tra(?:\slo)?" + SPACE),
maybe(DateCirca.Pattern(language) + SPACE), // (?:(?:Intorno\sal|circa)\s)?
maybe(oneof(Lookup <EnumDatePrefix> .Patterns(language), "prefix1") + SPACE),
group(ROMAN, "centuryMin"), // (?<centuryMin>[MCDLXVI]+)
oneof(new string[] { @"\s*[e\;\-\/]\s*", @"\sed?\slo\s" }), // separator
maybe(oneof(Lookup <EnumDatePrefix> .Patterns(language), "prefix2") + SPACE),
group(ROMAN, "centuryMax"), // (?<centuryMax>[MCDLXVI]+)
maybe(SPACE + @"sec(?:\.|olo)"),
maybe(SPACE + oneof(Lookup <EnumDateSuffix> .Patterns(language), "suffix")), // (?:\s(?<suffix>a\.?C\.?|d\.?C\.?))?
END
);
break;
}
case EnumLanguage.NL:
{
pattern = String.Concat(
START,
maybe(@"tussen" + SPACE),
maybe(DateCirca.Pattern(language) + SPACE),
maybe(oneof(Lookup <EnumDatePrefix> .Patterns(language), "prefix1") + SPACE), //
group(@"\d+", "centuryMin"),
oneof(new string[] { "e", "ste", "de" }),
maybe(SPACE + "eeuw"),
@"\s*(?:[e\;\-\/]|en)\s*", //separators
maybe(oneof(Lookup <EnumDatePrefix> .Patterns(language), "prefix2") + SPACE),
group(@"\d+", "centuryMax"),
oneof(new string[] { "e", "ste", "de" }),
SPACE,
"eeuw",
maybe(SPACE + oneof(Lookup <EnumDateSuffix> .Patterns(language), "suffix")),
END
);
break;
}
default:
{
pattern = String.Concat(
START, // ^
maybe(DateCirca.Pattern(language) + SPACE),
maybe(oneof(Lookup <EnumDatePrefix> .Patterns(language), "prefix1") + SPACE), //
group(@"\d+", "centuryMin"), // (?<centuryMin>\d+)
oneof(new string[] { "st", "nd", "rd", "th" }),
@"\s*(?:[e\;\-\/]|to)\s*", // separator
maybe(oneof(Lookup <EnumDatePrefix> .Patterns(language), "prefix2") + SPACE),
group(@"\d+", "centuryMax"), // (?<centuryMax>\d+)
oneof(new string[] { "st", "nd", "rd", "th" }),
SPACE,
"century", // century
maybe(SPACE + oneof(Lookup <EnumDateSuffix> .Patterns(language), "suffix")), // (?:\s(?<suffix>A\.?D\.?|B\.?C\.?))?
END // $
);
break;
}
}
return(pattern);
}
private static string GetPattern(EnumLanguage language = EnumLanguage.NONE)
{
string pattern = "";
switch (language)
{
case EnumLanguage.CY:
{
pattern = String.Concat(
START,
maybe(DateCirca.Pattern(language) + SPACE),
maybe(oneof(Lookup <EnumDatePrefix> .Patterns(language), "prefix") + SPACE),
group(@"\d+", "century"),
oneof(new string[] { "af", @"a?il", "ain", "ydd", @"f?ed", "eg" }),
SPACE,
"[cg]anrif",
maybe(SPACE + oneof(Lookup <EnumDateSuffix> .Patterns(language), "suffix")),
END
);
break;
}
case EnumLanguage.DE:
{
pattern = String.Concat(
START,
maybe(DateCirca.Pattern(language) + SPACE),
maybe(oneof(Lookup <EnumDatePrefix> .Patterns(language), "prefix") + SPACE),
group(@"\d+", "century"),
@"\.",
SPACE,
"Jahrhundert",
END
);
break;
}
case EnumLanguage.IT:
{
// ^(?:(?:C(?:\.|irca)|Intorno al)\s)?(?<millennium>[MCDLXVI]+)\s?(?:esimo|mo|°|º)?\smillennio(?:\s(?<suffix>a\.?C\.?|d\.?C\.?))?$
// eg XI secolo | secolo XI | XIesimo secolo | XImo secolo | 11 ° secolo
pattern = String.Concat(
START, // ^
maybe(DateCirca.Pattern(language) + SPACE), // (?:(?:C(?:\.|irca)|Intorno al)\s)?
maybe(oneof(Lookup <EnumDatePrefix> .Patterns(language), "prefix") + SPACE),
oneof(new string[] {
String.Concat(
@"sec(?:\.|olo)",
SPACE,
group(ROMAN, "century")
),
String.Concat(
group(ROMAN, "century"),
SPACE,
@"sec(?:\.|olo)"
),
String.Concat(
group(@"\d+", "century"),
maybe(SPACE),
maybe(oneof(new string[] { "esimo", "mo", "°", "º" })), // (?:esimo|mo|°|º)?
SPACE,
@"sec(?:\.|olo)"
),
group(ROMAN, "century")
}),
maybe(SPACE + oneof(Lookup <EnumDateSuffix> .Patterns(language), "suffix")), // (?:\s(?<suffix>a\.?C\.?|d\.?C\.?))?
END // $
);
break;
}
case EnumLanguage.FR:
{
// 11e siècle | XIe siècle av. J-C. | apr. J-C.
// pattern = @"^(?<century>[MCDLXVI]+|\d+)e\s+siècle(?:\s+(?<suffix>av\.\sJ\-C\.|apr\.\sJ\-C\.))?$";
pattern = String.Concat(
START,
maybe(DateCirca.Pattern(language) + SPACE),
maybe(oneof(Lookup <EnumDatePrefix> .Patterns(language), "prefix") + SPACE),
oneof(new string[] { ROMAN, @"\d+" }, "century"),
oneof(new string[] { "è?[mr]e", "er", "re", "[eè]", "n?de?", "o" }),
SPACE,
@"s(?:\.|iècle)",
maybe(SPACE + oneof(Lookup <EnumDateSuffix> .Patterns(language), "suffix")),
END
);
break;
}
case EnumLanguage.ES:
{
// XI siglo | siglo XI
//pattern = @"^(?:siglo\s+)?(?<century>[MCDLXVI]+|\d+)(?:\s+siglo)?$";
pattern = String.Concat(
START,
maybe(DateCirca.Pattern(language) + SPACE),
maybe(oneof(Lookup <EnumDatePrefix> .Patterns(language), "prefix") + SPACE),
maybe("Siglo" + SPACE),
oneof(new string[] { ROMAN, @"\d+" }, "century"),
maybe(SPACE + "Siglo"),
maybe(SPACE + oneof(Lookup <EnumDateSuffix> .Patterns(language), "suffix")),
END
);
break;
}
case EnumLanguage.NL:
{
pattern = String.Concat(
START,
maybe(DateCirca.Pattern(language) + SPACE),
maybe(oneof(Lookup <EnumDatePrefix> .Patterns(language), "prefix") + SPACE),
group(@"\d+", "century"),
oneof(new string[] { "e", "ste", "de" }),
SPACE,
"eeuw",
maybe(SPACE + oneof(Lookup <EnumDateSuffix> .Patterns(language), "suffix")),
END
);
break;
}
case EnumLanguage.SV:
{
// 1700-talet | 18:e århundradet | 18:e seklet | 1700-tal
pattern = String.Concat(
START,
maybe(DateCirca.Pattern(language) + SPACE),
maybe(oneof(Lookup <EnumDatePrefix> .Patterns(language), "prefix") + SPACE),
oneof(new string[] {
String.Concat(
group(@"\d+", "century"),
oneof(new string[] { ":a", ":e" }),
SPACE,
oneof(new string[] { "århundradet", "seklet" })
),
String.Concat(
group(@"\d+00", "century"),
@"-tal",
maybe("et")
)
}),
maybe(SPACE + oneof(Lookup <EnumDateSuffix> .Patterns(language), "suffix")),
END
);
break;
}
default:
{
//pattern = @"^(?:c(?:irca|\.)?\s+)?(?<centuryNo>\d+)(?:st|nd|rd|th)\s+(?:century|centuries)(?:\s+(?<suffix>ad|bc|ce))?$";
pattern = String.Concat(
START, // ^
maybe(DateCirca.Pattern(language) + SPACE),
maybe(oneof(Lookup <EnumDatePrefix> .Patterns(language), "prefix") + SPACE), // (?:(?:C(?:\.|irca)|Intorno al)\s)?
group(@"\d+", "century"), // (?<century>\d+)
oneof(new string[] { "st", "nd", "rd", "th" }),
SPACE,
"century", // century
maybe(SPACE + oneof(Lookup <EnumDateSuffix> .Patterns(language), "suffix")), // (?:\s(?<suffix>A\.?D\.?|B\.?C\.?))?
END // $
);
break;
}
}
return(pattern);
}
private static string GetPattern(EnumLanguage language = EnumLanguage.NONE)
{
string pattern = "";
switch (language)
{
case EnumLanguage.CY:
{
pattern = String.Concat(
START,
maybe(DateCirca.Pattern(language) + SPACE),
maybe(oneof(Lookup <EnumDatePrefix> .Patterns(language), "prefix") + SPACE),
group(@"\d+", "millennium"),
oneof(new string[] { "af", @"a?il", "ain", "ydd", @"f?ed", "eg" }),
SPACE,
"mileniwm",
maybe(SPACE + oneof(Lookup <EnumDateSuffix> .Patterns(language), "suffix")),
END
);
break;
}
case EnumLanguage.FR:
{
pattern = String.Concat(
START,
maybe(DateCirca.Pattern(language) + SPACE),
maybe(oneof(Lookup <EnumDatePrefix> .Patterns(language), "prefix") + SPACE),
oneof(new string[] { ROMAN, @"\d+" }, "millennium"),
oneof(new string[] { "è?[mr]e", "er", "re", "[eè]", "n?de?", "o" }),
SPACE,
"millénaire",
maybe(SPACE + oneof(Lookup <EnumDateSuffix> .Patterns(language), "suffix")),
END
);
break;
}
case EnumLanguage.IT:
// ^(?:(?:C(?:\.|irca)|Intorno al)\s)?(?<millennium>[MCDLXVI]+)\s?(?:esimo|mo|°|º)?\smillennio(?:\s(?<suffix>a\.?C\.?|d\.?C\.?))?$
pattern = String.Concat(
START,
maybe(DateCirca.Pattern(language) + SPACE),
maybe(oneof(Lookup <EnumDatePrefix> .Patterns(language), "prefix") + SPACE), // (?:(?:C(?:\.|irca)|Intorno al)\s)?
oneof(new string[] {
String.Concat(
"millennio",
SPACE,
oneof(new string[] { ROMAN, @"\d+" }, "millennium"),
maybe(SPACE),
maybe(oneof(new string[] { "esimo", "mo", "°", "º" })) // (?:esimo|mo|°|º)?
),
String.Concat(
oneof(new string[] { ROMAN, @"\d+" }, "millennium"),
maybe(SPACE),
maybe(oneof(new string[] { "esimo", "mo", "°", "º" })), // (?:esimo|mo|°|º)?
"millennio"
)
}),
maybe(SPACE + oneof(Lookup <EnumDateSuffix> .Patterns(language), "suffix")), // (?:\s(?<suffix>a\.?C\.?|d\.?C\.?))?
END // $
);
break;
default:
// ^(?:(?:C(?:\.|irca)|around|approx(?:\.|imately))\s)?(?<millennium>\d+)(?:st|nd|rd|th)\smillennium(?:\s(?<suffix>AD|BC|CE|BP))?$
pattern = String.Concat(
START,
maybe(DateCirca.Pattern(language) + SPACE),
maybe(oneof(Lookup <EnumDatePrefix> .Patterns(language), "prefix") + SPACE), // (?:(?:C(?:\.|irca)|around|approx(?:\.|imately))\s)?
group(@"\d+", "millennium"), // (?<millennium>\d+)
oneof(new string[] { "st", "nd", "rd", "th" }), // (?:st|nd|rd|th)
SPACE, // \s
"millennium", // millennium
maybe(SPACE + oneof(Lookup <EnumDateSuffix> .Patterns(language), "suffix")), // (?:\s(?<suffix>AD|BC|CE|BP))?
END // $
);
break;
}
return(pattern);
}
private static string GetPattern(EnumLanguage language = EnumLanguage.NONE)
{
string pattern = "";
switch (language)
{
case EnumLanguage.CY:
pattern = String.Concat(
START,
maybe(DateCirca.Pattern(language) + SPACE),
maybe(oneof(Lookup <EnumDatePrefix> .Patterns(language), "prefix") + SPACE),
oneof(Lookup <EnumOrdinal> .Patterns(language), "ordinal"),
SPACE,
"mileniwm",
maybe(SPACE + oneof(Lookup <EnumDateSuffix> .Patterns(language), "suffix")),
END
);
break;
case EnumLanguage.FR:
pattern = String.Concat(
START,
maybe(DateCirca.Pattern(language) + SPACE),
maybe(oneof(Lookup <EnumDatePrefix> .Patterns(language), "prefix") + SPACE),
oneof(Lookup <EnumOrdinal> .Patterns(language), "ordinal"),
SPACE,
"millénaire",
maybe(SPACE + oneof(Lookup <EnumDateSuffix> .Patterns(language), "suffix")),
END
);
break;
case EnumLanguage.IT:
pattern = String.Concat(
START, // ^
maybe(DateCirca.Pattern(language) + SPACE), // (?:(?:C(?:\.|irca)|Intorno al)\s)?
maybe(oneof(Lookup <EnumDatePrefix> .Patterns(language), "prefix") + SPACE),
oneof(new string[] {
@"millennio\s" + oneof(Lookup <EnumOrdinal> .Patterns(language), "ordinal"),
oneof(Lookup <EnumOrdinal> .Patterns(language), "ordinal") + @"\smillennio"
}),
maybe(SPACE + oneof(Lookup <EnumDateSuffix> .Patterns(language), "suffix")), // (?:\s(?<suffix>a\.?C\.?|d\.?C\.?))?
END // $
);
break;
default:
pattern = String.Concat(
START, // ^
maybe(DateCirca.Pattern(language) + SPACE),
maybe(oneof(Lookup <EnumDatePrefix> .Patterns(language), "prefix") + SPACE), // (?:
oneof(Lookup <EnumOrdinal> .Patterns(language), "ordinal"),
SPACE,
"millennium",
maybe(SPACE + oneof(Lookup <EnumDateSuffix> .Patterns(language), "suffix")),
END
);
break;
}
return(pattern);
}
private static string GetPattern(EnumLanguage language)
{
string pattern = "";
switch (language)
{
case EnumLanguage.CY:
// e.g. 1550au
pattern = String.Concat(
START, // ^
maybe(DateCirca.Pattern(language) + SPACE),
group(@"\d+0", "decade"), // (?<decade>\d+0)
@"au",
END
);
break;
case EnumLanguage.DE:
// ^(?:Um\s)?(?<decade>\d+0)\'?s$
// e.g. Um 1850's
pattern = String.Concat(
START, // ^
maybe(DateCirca.Pattern(language) + SPACE), // (?:Um\s)?
group(@"\d+0", "decade"), // (?<decade>\d+0)
@"\'?s", // \'?s
END // $
);
break;
case EnumLanguage.FR:
// ^(?:Vers\s)?(?<decade>\d+0)\'?s$
// e.g. Vers 1850's
pattern = String.Concat(
START, // ^
maybe(DateCirca.Pattern(language) + SPACE), // (?:Vers\s)?
@"les années\s",
group(@"\d+0", "decade"), // (?<decade>\d+0)
END // $
);
break;
case EnumLanguage.NL:
// ^(?:Circa\s)?(?<decade>\d+0)\'?s$ (not right)
pattern = String.Concat(
START, // ^
maybe(DateCirca.Pattern(language) + SPACE), // (?:Circa\s)
group(@"\d+0", "decade"),
@"\'?s",
END
);
break;
case EnumLanguage.SV:
// ^(?:C(?:\.|irka)?\s)?(?<decade>\d+0)\-talet$
pattern = String.Concat(
START,
maybe(DateCirca.Pattern(language) + SPACE),
group(@"\d+0", "decade"),
@"\-talet",
END
);
break;
case EnumLanguage.IT:
// ^(?:Intorno\sal|circa)?\s*decennio\s(?<decade>\d+[1-9]0)(?:esimo)?$
// e.g. "Intorno al decennio 1850esimo" => "around the decade of 1850's"
pattern = String.Concat(
START,
maybe(DateCirca.Pattern(language) + SPACE),
@"decennio\s",
group(@"\d+0", "decade"),
maybe("esimo"),
END
);
break;
default:
// ^(?:c(?:irca|\.|)\s*)?(?<decade>\d+[1-9]0)\'?s$
// e.g. "1850s" "circa 1920's"
pattern = String.Concat(
START,
maybe(DateCirca.Pattern(language) + SPACE),
group(@"\d+0", "decade"),
@"\'?s",
END
);
break;
}
return(pattern);
}