Skip to content

Commit

Permalink
[EN DateTimeV2] "the MM/DD[/YYYY]" resolution fix
Browse files Browse the repository at this point in the history
  • Loading branch information
@andrew-gradinari
andrew-gradinari committed May 8, 2023
1 parent 17de6bb commit 5b3fe87
Show file tree
Hide file tree
Showing 10 changed files with 446 additions and 12 deletions.
6 changes: 3 additions & 3 deletions .NET/Microsoft.Recognizers.Definitions.Common/English/DateTimeDefinitions.cs
View file
Original file line number Diff line number Diff line change
Expand Up @@ -139,8 +139,8 @@ public static class DateTimeDefinitions
public static readonly string DateExtractor4 = $@"\b{MonthNumRegex}\s*[/\\\-]\s*{DayRegex}[\.]?\s*[/\\\-]\s*{DateYearRegex}";
public static readonly string DateExtractor5 = $@"\b({DayPrefix}(\s*,)?\s+)?{DayRegex}\s*[/\\\-\.]\s*({MonthNumRegex}|{MonthRegex})\s*[/\\\-\.]\s*{DateYearRegex}(?!\s*[/\\\-\.]\s*\d+)";
public static readonly string DateExtractor6 = $@"(?<={DatePreposition}\s+)({StrictRelativeRegex}\s+)?({DayPrefix}\s+)?{MonthNumRegex}[\-\.]{DayRegex}(?![%]){BaseDateTime.CheckDecimalRegex}\b";
public static readonly string DateExtractor7L = $@"\b({DayPrefix}(\s*,)?\s+)?{MonthNumRegex}\s*/\s*{DayRegex}{DateExtractorYearTermRegex}(?![%])\b";
public static readonly string DateExtractor7S = $@"\b({DayPrefix}(\s*,)?\s+)?{MonthNumRegex}\s*/\s*{DayRegex}(?![%]){BaseDateTime.CheckDecimalRegex}\b";
public static readonly string DateExtractor7L = $@"\b({DayPrefix}(\s*,)?\s+)?(the\s+)?{MonthNumRegex}\s*/\s*{DayRegex}{DateExtractorYearTermRegex}(?![%])\b";
public static readonly string DateExtractor7S = $@"\b({DayPrefix}(\s*,)?\s+)?(the\s+)?{MonthNumRegex}\s*/\s*{DayRegex}(?![%]){BaseDateTime.CheckDecimalRegex}\b";
public static readonly string DateExtractor8 = $@"(?<={DatePreposition}\s+)({StrictRelativeRegex}\s+)?({DayPrefix}\s+)?{DayRegex}[\\\-]{MonthNumRegex}(?![%]){BaseDateTime.CheckDecimalRegex}\b";
public static readonly string DateExtractor9L = $@"\b({DayPrefix}(\s*,)?\s+)?{DayRegex}\s*/\s*{MonthNumRegex}{DateExtractorYearTermRegex}(?![%])\b";
public static readonly string DateExtractor9S = $@"\b({DayPrefix}(\s*,)?\s+)?{DayRegex}\s*/\s*{MonthNumRegex}{BaseDateTime.CheckDecimalRegex}(?![%])\b";
Expand Down Expand Up @@ -926,4 +926,4 @@ public static class DateTimeDefinitions
public const string QuarterTypeRegex = @"(quarter(s|ly)?)$";
public const string YearTypeRegex = @"((years?|annual)(ly)?)$";
}
}
}
4 changes: 2 additions & 2 deletions ...time/src/main/java/com/microsoft/recognizers/text/datetime/resources/EnglishDateTime.java
View file
Original file line number Diff line number Diff line change
Expand Up @@ -412,13 +412,13 @@ public class EnglishDateTime {
.replace("{StrictRelativeRegex}", StrictRelativeRegex)
.replace("{BaseDateTime.CheckDecimalRegex}", BaseDateTime.CheckDecimalRegex);

public static final String DateExtractor7L = "\\b({DayPrefix}(\\s*,)?\\s+)?{MonthNumRegex}\\s*/\\s*{DayRegex}{DateExtractorYearTermRegex}(?![%])\\b"
public static final String DateExtractor7L = "\\b({DayPrefix}(\\s*,)?\\s+)?(the\\s+)?{MonthNumRegex}\\s*/\\s*{DayRegex}{DateExtractorYearTermRegex}(?![%])\\b"
.replace("{MonthNumRegex}", MonthNumRegex)
.replace("{DayRegex}", DayRegex)
.replace("{DayPrefix}", DayPrefix)
.replace("{DateExtractorYearTermRegex}", DateExtractorYearTermRegex);

public static final String DateExtractor7S = "\\b({DayPrefix}(\\s*,)?\\s+)?{MonthNumRegex}\\s*/\\s*{DayRegex}(?![%]){BaseDateTime.CheckDecimalRegex}\\b"
public static final String DateExtractor7S = "\\b({DayPrefix}(\\s*,)?\\s+)?(the\\s+)?{MonthNumRegex}\\s*/\\s*{DayRegex}(?![%]){BaseDateTime.CheckDecimalRegex}\\b"
.replace("{MonthNumRegex}", MonthNumRegex)
.replace("{DayRegex}", DayRegex)
.replace("{DayPrefix}", DayPrefix)
Expand Down
4 changes: 2 additions & 2 deletions JavaScript/packages/recognizers-date-time/src/resources/englishDateTime.ts
View file
Original file line number Diff line number Diff line change
Expand Up @@ -129,8 +129,8 @@ export namespace EnglishDateTime {
export const DateExtractor4 = `\\b${MonthNumRegex}\\s*[/\\\\\\-]\\s*${DayRegex}[\\.]?\\s*[/\\\\\\-]\\s*${DateYearRegex}`;
export const DateExtractor5 = `\\b(${DayPrefix}(\\s*,)?\\s+)?${DayRegex}\\s*[/\\\\\\-\\.]\\s*(${MonthNumRegex}|${MonthRegex})\\s*[/\\\\\\-\\.]\\s*${DateYearRegex}(?!\\s*[/\\\\\\-\\.]\\s*\\d+)`;
export const DateExtractor6 = `(?<=${DatePreposition}\\s+)(${StrictRelativeRegex}\\s+)?(${DayPrefix}\\s+)?${MonthNumRegex}[\\-\\.]${DayRegex}(?![%])${BaseDateTime.CheckDecimalRegex}\\b`;
export const DateExtractor7L = `\\b(${DayPrefix}(\\s*,)?\\s+)?${MonthNumRegex}\\s*/\\s*${DayRegex}${DateExtractorYearTermRegex}(?![%])\\b`;
export const DateExtractor7S = `\\b(${DayPrefix}(\\s*,)?\\s+)?${MonthNumRegex}\\s*/\\s*${DayRegex}(?![%])${BaseDateTime.CheckDecimalRegex}\\b`;
export const DateExtractor7L = `\\b(${DayPrefix}(\\s*,)?\\s+)?(the\\s+)?${MonthNumRegex}\\s*/\\s*${DayRegex}${DateExtractorYearTermRegex}(?![%])\\b`;
export const DateExtractor7S = `\\b(${DayPrefix}(\\s*,)?\\s+)?(the\\s+)?${MonthNumRegex}\\s*/\\s*${DayRegex}(?![%])${BaseDateTime.CheckDecimalRegex}\\b`;
export const DateExtractor8 = `(?<=${DatePreposition}\\s+)(${StrictRelativeRegex}\\s+)?(${DayPrefix}\\s+)?${DayRegex}[\\\\\\-]${MonthNumRegex}(?![%])${BaseDateTime.CheckDecimalRegex}\\b`;
export const DateExtractor9L = `\\b(${DayPrefix}(\\s*,)?\\s+)?${DayRegex}\\s*/\\s*${MonthNumRegex}${DateExtractorYearTermRegex}(?![%])\\b`;
export const DateExtractor9S = `\\b(${DayPrefix}(\\s*,)?\\s+)?${DayRegex}\\s*/\\s*${MonthNumRegex}${BaseDateTime.CheckDecimalRegex}(?![%])\\b`;
Expand Down
4 changes: 2 additions & 2 deletions Patterns/English/English-DateTime.yaml
View file
Original file line number Diff line number Diff line change
Expand Up @@ -306,10 +306,10 @@ DateExtractor6: !nestedRegex
def: (?<={DatePreposition}\s+)({StrictRelativeRegex}\s+)?({DayPrefix}\s+)?{MonthNumRegex}[\-\.]{DayRegex}(?![%]){BaseDateTime.CheckDecimalRegex}\b
references: [ MonthNumRegex, DayRegex, DayPrefix, DatePreposition, StrictRelativeRegex, BaseDateTime.CheckDecimalRegex ]
DateExtractor7L: !nestedRegex
def: \b({DayPrefix}(\s*,)?\s+)?{MonthNumRegex}\s*/\s*{DayRegex}{DateExtractorYearTermRegex}(?![%])\b
def: \b({DayPrefix}(\s*,)?\s+)?(the\s+)?{MonthNumRegex}\s*/\s*{DayRegex}{DateExtractorYearTermRegex}(?![%])\b
references: [ MonthNumRegex, DayRegex, DayPrefix, DateExtractorYearTermRegex ]
DateExtractor7S: !nestedRegex
def: \b({DayPrefix}(\s*,)?\s+)?{MonthNumRegex}\s*/\s*{DayRegex}(?![%]){BaseDateTime.CheckDecimalRegex}\b
def: \b({DayPrefix}(\s*,)?\s+)?(the\s+)?{MonthNumRegex}\s*/\s*{DayRegex}(?![%]){BaseDateTime.CheckDecimalRegex}\b
references: [ MonthNumRegex, DayRegex, DayPrefix, BaseDateTime.CheckDecimalRegex ]
# The only difference between 7L and 7S is whether "Year" part is required
# We have both the long and short Regex because we would like to catch both "11/20, 12" and "11/20, 12/20"
Expand Down
4 changes: 2 additions & 2 deletions Python/libraries/recognizers-date-time/recognizers_date_time/resources/english_date_time.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -132,8 +132,8 @@ class EnglishDateTime:
DateExtractor4 = f'\\b{MonthNumRegex}\\s*[/\\\\\\-]\\s*{DayRegex}[\\.]?\\s*[/\\\\\\-]\\s*{DateYearRegex}'
DateExtractor5 = f'\\b({DayPrefix}(\\s*,)?\\s+)?{DayRegex}\\s*[/\\\\\\-\\.]\\s*({MonthNumRegex}|{MonthRegex})\\s*[/\\\\\\-\\.]\\s*{DateYearRegex}(?!\\s*[/\\\\\\-\\.]\\s*\\d+)'
DateExtractor6 = f'(?<={DatePreposition}\\s+)({StrictRelativeRegex}\\s+)?({DayPrefix}\\s+)?{MonthNumRegex}[\\-\\.]{DayRegex}(?![%]){BaseDateTime.CheckDecimalRegex}\\b'
DateExtractor7L = f'\\b({DayPrefix}(\\s*,)?\\s+)?{MonthNumRegex}\\s*/\\s*{DayRegex}{DateExtractorYearTermRegex}(?![%])\\b'
DateExtractor7S = f'\\b({DayPrefix}(\\s*,)?\\s+)?{MonthNumRegex}\\s*/\\s*{DayRegex}(?![%]){BaseDateTime.CheckDecimalRegex}\\b'
DateExtractor7L = f'\\b({DayPrefix}(\\s*,)?\\s+)?(the\\s+)?{MonthNumRegex}\\s*/\\s*{DayRegex}{DateExtractorYearTermRegex}(?![%])\\b'
DateExtractor7S = f'\\b({DayPrefix}(\\s*,)?\\s+)?(the\\s+)?{MonthNumRegex}\\s*/\\s*{DayRegex}(?![%]){BaseDateTime.CheckDecimalRegex}\\b'
DateExtractor8 = f'(?<={DatePreposition}\\s+)({StrictRelativeRegex}\\s+)?({DayPrefix}\\s+)?{DayRegex}[\\\\\\-]{MonthNumRegex}(?![%]){BaseDateTime.CheckDecimalRegex}\\b'
DateExtractor9L = f'\\b({DayPrefix}(\\s*,)?\\s+)?{DayRegex}\\s*/\\s*{MonthNumRegex}{DateExtractorYearTermRegex}(?![%])\\b'
DateExtractor9S = f'\\b({DayPrefix}(\\s*,)?\\s+)?{DayRegex}\\s*/\\s*{MonthNumRegex}{BaseDateTime.CheckDecimalRegex}(?![%])\\b'
Expand Down
44 changes: 44 additions & 0 deletions Specs/DateTime/English/DateExtractor.json
View file
Original file line number Diff line number Diff line change
Expand Up @@ -1680,5 +1680,49 @@
"Length": 17
}
]
},
{
"Input": "the photograph appeared in the 01/07 issue of the magazine",
"Results": [
{
"Text": "the 01/07",
"Type": "date",
"Start": 27,
"Length": 9
}
]
},
{
"Input": "the contract is expected to start on 10/11",
"Results": [
{
"Text": "10/11",
"Type": "date",
"Start": 37,
"Length": 5
}
]
},
{
"Input": "the software used in the 11/3/2020 election can be easily hacked",
"Results": [
{
"Text": "the 11/3/2020",
"Type": "date",
"Start": 21,
"Length": 13
}
]
},
{
"Input": "this article was published on 06/10/2020",
"Results": [
{
"Text": "06/10/2020",
"Type": "date",
"Start": 30,
"Length": 10
}
]
}
]
95 changes: 94 additions & 1 deletion Specs/DateTime/English/DateParser.json
View file
Original file line number Diff line number Diff line change
Expand Up @@ -3143,5 +3143,98 @@
"Length": 9
}
]
},
{
"Input": "the photograph appeared in the 01/07 issue of the magazine",
"Context": {
"ReferenceDateTime": "2023-05-05T00:00:00"
},
"Results": [
{
"Text": "the 01/07",
"Type": "date",
"Value": {
"Timex": "XXXX-01-07",
"FutureResolution": {
"date": "2024-01-07"
},
"PastResolution": {
"date": "2023-01-07"
}
},
"Start": 27,
"Length": 9
}
]
},
{
"Input": "the contract is expected to start on 10/11",
"Context": {
"ReferenceDateTime": "2023-05-05T00:00:00"
},
"Results": [
{
"Text": "10/11",
"Type": "date",
"Value": {
"Timex": "XXXX-10-11",
"FutureResolution": {
"date": "2023-10-11"
},
"PastResolution": {
"date": "2022-10-11"
}
},
"Start": 37,
"Length": 5
}
]
},
{
"Input": "the software used in the 11/3/2020 election can be easily hacked",
"Context": {
"ReferenceDateTime": "2023-05-05T00:00:00"
},
"NotSupported": "java,javascript",
"Results": [
{
"Text": "the 11/3/2020",
"Type": "date",
"Value": {
"Timex": "2020-11-03",
"FutureResolution": {
"date": "2020-11-03"
},
"PastResolution": {
"date": "2020-11-03"
}
},
"Start": 21,
"Length": 13
}
]
},
{
"Input": "this article was published on 06/10/2020",
"Context": {
"ReferenceDateTime": "2023-05-05T00:00:00"
},
"Results": [
{
"Text": "06/10/2020",
"Type": "date",
"Value": {
"Timex": "2020-06-10",
"FutureResolution": {
"date": "2020-06-10"
},
"PastResolution": {
"date": "2020-06-10"
}
},
"Start": 30,
"Length": 10
}
]
}
]
]
103 changes: 103 additions & 0 deletions Specs/DateTime/English/DateTimeModel.json
View file
Original file line number Diff line number Diff line change
Expand Up @@ -25850,5 +25850,108 @@
}
}
]
},
{
"Input": "the photograph appeared in the 01/07 issue of the magazine",
"Context": {
"ReferenceDateTime": "2023-05-05T00:00:00"
},
"Results": [
{
"Start": 27,
"End": 35,
"Resolution": {
"values": [
{
"timex": "XXXX-01-07",
"type": "date",
"value": "2023-01-07"
},
{
"timex": "XXXX-01-07",
"type": "date",
"value": "2024-01-07"
}
]
},
"Text": "the 01/07",
"TypeName": "datetimeV2.date"
}
]
},
{
"Input": "the contract is expected to start on 10/11",
"Context": {
"ReferenceDateTime": "2023-05-05T00:00:00"
},
"Results": [
{
"Start": 37,
"End": 41,
"Resolution": {
"values": [
{
"timex": "XXXX-10-11",
"type": "date",
"value": "2022-10-11"
},
{
"timex": "XXXX-10-11",
"type": "date",
"value": "2023-10-11"
}
]
},
"Text": "10/11",
"TypeName": "datetimeV2.date"
}
]
},
{
"Input": "the software used in the 11/3/2020 election can be easily hacked",
"Context": {
"ReferenceDateTime": "2023-05-05T00:00:00"
},
"NotSupported": "java,javascript",
"Results": [
{
"Start": 21,
"End": 33,
"Resolution": {
"values": [
{
"timex": "2020-11-03",
"type": "date",
"value": "2020-11-03"
}
]
},
"Text": "the 11/3/2020",
"TypeName": "datetimeV2.date"
}
]
},
{
"Input": "this article was published on 06/10/2020",
"Context": {
"ReferenceDateTime": "2023-05-05T00:00:00"
},
"Results": [
{
"Start": 30,
"End": 39,
"Resolution": {
"values": [
{
"timex": "2020-06-10",
"type": "date",
"value": "2020-06-10"
}
]
},
"Text": "06/10/2020",
"TypeName": "datetimeV2.date"
}
]
}
]
Loading

0 comments on commit 5b3fe87

Please sign in to comment.