Skip to content

Commit

Permalink
Multiple small fixes and re-gen of resources across platforms (#2944)
Browse files Browse the repository at this point in the history
* Adding "abd dolar" in Turkish according to user feedback (#2419)
 
* Fix German night terms (#2906)

* Support 't' as abbreviation for ton (#2899)

* Enabling French DateTime extractor specs that pass

* Adding mex$ as recognized currency

* Adding support for "as soon as possible" in French

* Re-gen resources across platforms

* Auto PIP fixes
  • Loading branch information
tellarin authored May 6, 2022
1 parent 87d6c7e commit 4991750
Show file tree
Hide file tree
Showing 76 changed files with 712 additions and 315 deletions.
Original file line number Diff line number Diff line change
Expand Up @@ -158,13 +158,14 @@ public static class NumbersWithUnitDefinitions
{ @"Barrel", @"vat|vaten" },
{ @"Gallon", @"-gallon|gallon" },
{ @"Metric ton", @"metrische ton" },
{ @"Ton", @"-ton|ton" },
{ @"Ton", @"-ton|ton|t" },
{ @"Pound", @"-pond|pond" },
{ @"Ounce", @"-ons|ons" }
};
public static readonly IList<string> AmbiguousWeightUnitList = new List<string>
{
@"g",
@"t",
@"oz"
};
public static readonly Dictionary<string, string> CurrencySuffixList = new Dictionary<string, string>
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -243,7 +243,7 @@ public static class NumbersWithUnitDefinitions
{ @"Cuban convertible peso", @"cuban convertible pesos|cuban convertible peso|cuc|cuba convertible pesos|cuba convertible peso" },
{ @"Cuban peso", @"cuban pesos|cuban peso|cup|cuba pesos|cuba peso" },
{ @"Dominican peso", @"dominican pesos|dominican peso|dop|dominica pesos|dominica peso" },
{ @"Mexican peso", @"mexican pesos|mexican peso|mxn|mexico pesos|mexico peso|mxn$" },
{ @"Mexican peso", @"mexican pesos|mexican peso|mxn|mexico pesos|mexico peso|mxn$|mxn $|mex$" },
{ @"Philippine peso", @"piso|philippine pesos|philippine peso|₱|php" },
{ @"Uruguayan peso", @"uruguayan pesos|uruguayan peso|uyu" },
{ @"Peso", @"pesos|peso" },
Expand Down Expand Up @@ -586,7 +586,7 @@ public static class NumbersWithUnitDefinitions
{ @"Brazilian Real", @"R$" },
{ @"United States dollar", @"united states $|us$|us $|u.s. $|u.s $|usd$" },
{ @"East Caribbean dollar", @"east caribbean $" },
{ @"Mexican peso", @"mxn$" },
{ @"Mexican peso", @"mxn$|mxn $|mex$" },
{ @"Australian dollar", @"australian $|australia $" },
{ @"Bahamian dollar", @"bahamian $|bahamia $" },
{ @"Barbadian dollar", @"barbadian $|barbadin $" },
Expand Down Expand Up @@ -862,7 +862,7 @@ public static class NumbersWithUnitDefinitions
{ @"Microgram", @"μg|microgram|micrograms|micro gram|micro grams|microgramme|microgrammes|mcg" },
{ @"Gallon", @"-gallon|gallons|gallon|gal" },
{ @"Metric ton", @"metric tons|metric ton" },
{ @"Ton", @"-ton|ton|tons|tonne|tonnes" },
{ @"Ton", @"-ton|ton|tons|tonne|tonnes|t" },
{ @"Pound", @"pound|pounds|lb|lbs" },
{ @"Ounce", @"-ounce|ounce|oz|ounces" },
{ @"Grain", @"grain|grains|gr" },
Expand All @@ -876,6 +876,7 @@ public static class NumbersWithUnitDefinitions
public static readonly IList<string> AmbiguousWeightUnitList = new List<string>
{
@"g",
@"t",
@"gr",
@"oz",
@"stone",
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -157,7 +157,7 @@ public static class DateTimeDefinitions
public static readonly string SpecificTimeOfDayRegex = $@"\b(({RelativeRegex}\s+{TimeOfDayRegex})|({TimeOfDayRegex}\s*({NextSuffixRegex}))\b|\b(du )?soir)s?\b";
public static readonly string TimeFollowedUnit = $@"^\s*{TimeUnitRegex}";
public static readonly string TimeNumberCombinedWithUnit = $@"\b(?<num>\d+(\.\d*)?){TimeUnitRegex}";
public const string NowRegex = @"\b(?<now>(ce\s+)?moment|maintenant|d[eè]s que possible|dqp|r[eé]cemment|auparavant)\b";
public const string NowRegex = @"\b(?<now>(ce\s+)?moment|maintenant|(d[eè]s|aussit[oô]t) que possible|dqp|r[eé]cemment|auparavant|le plus tôt( que)? possible)\b";
public const string SuffixRegex = @"^\s*((dans\s+l[ea]\s+)|(en\s+)|(d(u|\'))?(matin([eé]e)?|apr[eè]s-midi|soir[eé]e|nuit))\b";
public const string DateTimeTimeOfDayRegex = @"\b(?<timeOfDay>matin([eé]e)?|apr[eè]s-midi|nuit|soir)\b";
public static readonly string DateTimeSpecificTimeOfDayRegex = $@"\b(({RelativeRegex}\s+{DateTimeTimeOfDayRegex})\b|\b(ce(tte)?\s+)(soir|nuit))\b";
Expand Down Expand Up @@ -202,6 +202,7 @@ public static class DateTimeDefinitions
public const string ToTokenRegex = @"\b(moins|[aà]$)\b";
public const string AMTimeRegex = @"(?<am>matin([ée]e)?)";
public const string PMTimeRegex = @"\b(?<pm>(d'|l')?apr[eè]s-midi|nuit|((\s*ce|du)\s+)?soir)\b";
public const string AsapTimeRegex = @"((d[eè]s|le plus t[oô]t|aussit[oô]t)( que)? possible|dqp)";
public const string BeforeRegex = @"\b(avant)\b";
public const string BeforeRegex2 = @"\b(entre\s*(le|la(s)?)?)\b";
public const string AfterRegex = @"\b(apres)\b";
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -654,7 +654,6 @@ public static class NumbersWithUnitDefinitions
};
public static readonly IList<string> AmbiguousLengthUnitList = new List<string>
{
@"m",
@"m.",
@"yard",
@"yards",
Expand All @@ -674,6 +673,12 @@ public static class NumbersWithUnitDefinitions
{ @"Pied par seconde", @"ft/s|pied par seconde|pieds par seconde|pied/s|pieds/s" },
{ @"Pied par minute", @"pieds/minute|pied/minute|ft/minute|ft/min|pied/min" }
};
public static readonly IList<string> AmbiguousSpeedUnitList = new List<string>
{
@"noeud",
@"noeuds",
@"nuds"
};
public static readonly Dictionary<string, string> TemperatureSuffixList = new Dictionary<string, string>
{
{ @"Kelvin", @"k|K|kelvin" },
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -789,7 +789,7 @@ public static class DateTimeDefinitions
public static readonly IList<string> NightTermList = new List<string>
{
@"nacht",
@"nacths",
@"nachts",
@"primetime"
};
public static readonly IList<string> SameDayTerms = new List<string>
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -791,7 +791,7 @@ public static class NumbersWithUnitDefinitions
};
public static readonly Dictionary<string, string> WeightSuffixList = new Dictionary<string, string>
{
{ @"Tonelada métrica", @"tonelada métrica|tonelada metrica|toneladas métricas|toneladas metricas|t métrica|t metrica|t métricas|t metricas|t.métrica|t.metrica|t.métricas|t.metricas" },
{ @"Tonelada métrica", @"tonelada métrica|tonelada metrica|toneladas métricas|toneladas metricas|t métrica|t metrica|t métricas|t metricas|t.métrica|t.metrica|t.métricas|t.metricas|t. metrica|t. métrica" },
{ @"Tonelada", @"ton|tonelada|toneladas|t" },
{ @"Quilograma", @"kg|quilograma|quilogramas|quilo|quilos|kilo|kilos" },
{ @"Hectograma", @"hg|hectograma|hectogramas" },
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -252,7 +252,7 @@ public static class NumbersWithUnitDefinitions
{ @"Rupia de Mauricio", @"rupia de Mauricio|rupias de Mauricio|mur" },
{ @"Uguiya", @"uguiya|uguiyas|mro" },
{ @"Jum", @"jum|jums" },
{ @"Peso mexicano", @"peso mexicano|pesos mexicanos|mxn" },
{ @"Peso mexicano", @"peso mexicano|pesos mexicanos|mxn|mxn$|mxn $|mex$" },
{ @"Centavo mexicano", @"centavo mexicano|centavos mexicanos" },
{ @"Leu moldavo", @"leu moldavo|lei moldavos|mdl" },
{ @"Ban moldavo", @"ban moldavo|bani moldavos" },
Expand Down Expand Up @@ -666,6 +666,7 @@ public static class NumbersWithUnitDefinitions
{ @"Dólar namibio", @"n$|nad" },
{ @"Dólar de las Islas Salomón", @"si$|sbd" },
{ @"Nuevo dólar taiwanés", @"nt$|twd" },
{ @"Peso mexicano", @"mxn|mxn$|mxn $|mex$" },
{ @"Real brasileño", @"r$|brl" },
{ @"Guaraní", @"₲|gs.|pyg" },
{ @"Dólar trinitense", @"tt$|ttd" },
Expand Down Expand Up @@ -797,8 +798,8 @@ public static class NumbersWithUnitDefinitions
};
public static readonly Dictionary<string, string> WeightSuffixList = new Dictionary<string, string>
{
{ @"Tonelada métrica", @"tonelada métrica|toneladas métricas" },
{ @"Tonelada", @"ton|tonelada|toneladas" },
{ @"Tonelada métrica", @"tonelada métrica|toneladas métricas|t.métrica|t métrica|t. métrica|tonelada metrica|toneladas metricas|t.metrica|t metrica|t. metrica" },
{ @"Tonelada", @"ton|tonelada|toneladas|t" },
{ @"Kilogramo", @"kg|kilogramo|kilogramos" },
{ @"Hectogramo", @"hg|hectogramo|hectogramos" },
{ @"Decagramo", @"dag|decagramo|decagramos" },
Expand All @@ -814,6 +815,11 @@ public static class NumbersWithUnitDefinitions
{ @"Grano", @"grano|granos" },
{ @"Quilate", @"ct|quilate|quilates" }
};
public static readonly IList<string> AmbiguousWeightUnitList = new List<string>
{
@"g",
@"t"
};
public static readonly Dictionary<string, string> AngleSuffixList = new Dictionary<string, string>
{
{ @"Degree", @"grado|grados|°" },
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -1096,9 +1096,7 @@ public static class DateTimeDefinitions
public static readonly string[] DurationDateRestrictions = { @"bugün", @"şimdi", @"şu an" };
public static readonly Dictionary<string, string> AmbiguityFiltersDict = new Dictionary<string, string>
{
{ @"\bmorning|afternoon|evening|night|day\b", @"\b(good\s+(morning|afternoon|evening|night|day))|(nighty\s+night)\b" },
{ @"\bnow\b", @"\b(^now,)|\b((is|are)\s+now\s+for|for\s+now)\b" },
{ @"\bmay\b", @"\b((^may i)|(i|you|he|she|we|they)\s+may|(may\s+((((also|not|(also not)|well)\s+)?(be|ask|contain|constitute|email|e-mail|take|have|result|involve|get|work|reply|differ))|(or may not))))\b" }
{ @"\bmart\b", @"\b(martin)\b" }
};
public static readonly IList<string> MorningTermList = new List<string>
{
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -278,7 +278,7 @@ public static class NumbersWithUnitDefinitions
{ @"Pound", @"pound|sterlin|£|sterline|sterlinde|sterlinden|sterlini|sterlinin|sterlindir|sterlindi|sterlinmiş" },
{ @"Shilling", @"şilin|şiline|şilinde|şilinden|şilini|şilinin|şilindir|şilindi|şilinmiş" },
{ @"Penny", @"peni|peniye|penide|peniden|peniyi|peninin|penidir|peniydi|peniymiş" },
{ @"United States dollar", @"abd doları|a.b.d. doları|amerika birleşik devletleri doları|amerikan doları|usd|abd $|a.b.d. $|abd$|a.b.d.$|abd dolarına|abd dolarında|abd dolarından|abd dolarını|abd dolarının|abd dolarıdır|abd dolarıydı|abd dolarıymış|a.b.d. dolarına|a.b.d. dolarında|a.b.d. dolarından|a.b.d. dolarını|a.b.d. dolarının|a.b.d. dolarıdır|a.b.d. dolarıydı|a.b.d. dolarıymış|amerika birleşik devletleri dolarına|amerika birleşik devletleri dolarında|amerika birleşik devletleri dolarından|amerika birleşik devletleri dolarını|amerika birleşik devletleri dolarının|amerika birleşik devletleri dolarıdır|amerika birleşik devletleri dolarıydı|amerika birleşik devletleri dolarıymış|amerikan dolarına|amerikan dolarında|amerikan dolarından|amerikan dolarını|amerikan dolarının|amerikan dolarıdır|amerikan dolarıydı|amerikan dolarıymış" },
{ @"United States dollar", @"abd doları|abd dolar|a.b.d. doları|a.b.d. dolar|amerika birleşik devletleri doları|amerika birleşik devletleri dolar|amerikan doları|amerikan dolar|usd|abd $|a.b.d. $|abd$|a.b.d.$|abd dolarına|abd dolarında|abd dolarından|abd dolarını|abd dolarının|abd dolarıdır|abd dolarıydı|abd dolarıymış|a.b.d. dolarına|a.b.d. dolarında|a.b.d. dolarından|a.b.d. dolarını|a.b.d. dolarının|a.b.d. dolarıdır|a.b.d. dolarıydı|a.b.d. dolarıymış|amerika birleşik devletleri dolarına|amerika birleşik devletleri dolarında|amerika birleşik devletleri dolarından|amerika birleşik devletleri dolarını|amerika birleşik devletleri dolarının|amerika birleşik devletleri dolarıdır|amerika birleşik devletleri dolarıydı|amerika birleşik devletleri dolarıymış|amerikan dolarına|amerikan dolarında|amerikan dolarından|amerikan dolarını|amerikan dolarının|amerikan dolarıdır|amerikan dolarıydı|amerikan dolarıymış" },
{ @"East Caribbean dollar", @"doğu karayip doları|xcd|doğu karayip $|doğu karayip dolarına|doğu karayip dolarında|doğu karayip dolarından|doğu karayip dolarını|doğu karayip dolarının|doğu karayip dolarıdır|doğu karayip dolarıydı|doğu karayip dolarıymış" },
{ @"Australian dollar", @"avustralya doları|aud|avustralya $|avustralya$|avustralya dolarına|avustralya dolarında|avustralya dolarından|avustralya dolarını|avustralya dolarının|avustralya dolarıdır|avustralya dolarıydı|avustralya dolarıymış" },
{ @"Bahamian dollar", @"bahama doları|bsd|bahama $|bahama$|bahama dolarına|bahama dolarında|bahama dolarından|bahama dolarını|bahama dolarının|bahama dolarıdır|bahama dolarıydı|bahama dolarıymış" },
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -7,6 +7,7 @@

using Microsoft.Recognizers.Definitions.French;
using Microsoft.Recognizers.Text.DateTime.Utilities;
using Microsoft.Recognizers.Text.Utilities;

namespace Microsoft.Recognizers.Text.DateTime.French
{
Expand All @@ -20,6 +21,9 @@ public class FrenchDateTimeParserConfiguration : BaseDateTimeOptionsConfiguratio

private const RegexOptions RegexFlags = RegexOptions.Singleline | RegexOptions.ExplicitCapture;

private static readonly Regex AsapTimeRegex =
new Regex(DateTimeDefinitions.AsapTimeRegex, RegexFlags);

public FrenchDateTimeParserConfiguration(ICommonDateTimeParserConfiguration config)
: base(config)
{
Expand Down Expand Up @@ -143,8 +147,7 @@ public bool GetMatchedNowTimex(string text, out string timex)
{
timex = "PAST_REF";
}
else if (trimmedText.Equals("dès que possible", StringComparison.Ordinal) ||
trimmedText.Equals("dqp", StringComparison.Ordinal))
else if (AsapTimeRegex.IsExactMatch(trimmedText, trim: true))
{
timex = "FUTURE_REF";
}
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -12,6 +12,8 @@ public class WeightExtractorConfiguration : SpanishNumberWithUnitExtractorConfig
{
public static readonly ImmutableDictionary<string, string> WeightSuffixList = NumbersWithUnitDefinitions.WeightSuffixList.ToImmutableDictionary();

public static readonly ImmutableList<string> AmbiguousValues = NumbersWithUnitDefinitions.AmbiguousWeightUnitList.ToImmutableList();

public WeightExtractorConfiguration()
: this(new CultureInfo(Culture.Spanish))
{
Expand All @@ -26,7 +28,7 @@ public WeightExtractorConfiguration(CultureInfo ci)

public override ImmutableDictionary<string, string> PrefixList => null;

public override ImmutableList<string> AmbiguousUnitList => null;
public override ImmutableList<string> AmbiguousUnitList => AmbiguousValues;

public override string ExtractType => Constants.SYS_UNIT_WEIGHT;
}
Expand Down
Loading

0 comments on commit 4991750

Please sign in to comment.