Added support for timezone and calendar extensions to rfc3339 strings

Author: ericallam

README.md

@@ -157,6 +157,43 @@ The following table illustrates the results of different Date/Time strings
 | `"Mon, 02 Jan 2017 06:00:00 -0800"` | rfc2822 | datetime |
 | `"Mon, 02 Jan 2017 06:00:00 PST"`   | rfc2822 | datetime |
 
+Timezone and Calendar extensions for rfc3339 date/times are also detected:
+
+```js
+inferType("2022-02-28T11:06:00.092121729+08:00[Asia/Shanghai][u-ca=chinese]");
+```
+
+Will result in
+
+```json
+{
+  "name": "string",
+  "value": "2022-02-28T11:06:00.092121729+08:00[Asia/Shanghai][u-ca=chinese]",
+  "format": {
+    "name": "datetime",
+    "parts": "datetime",
+    "variant": "rfc3339",
+    "extensions": ["timezone", "calendar"]
+  }
+}
+```
+
+This is useful for knowing when you can use `Temporal.ZonedDateTime` in the new [Temporal](https://tc39.es/proposal-temporal/docs/index.html) ECMAScript proposal:
+
+```js
+const inferredType = inferType("2022-02-28T11:06:00.092121729+08:00[Asia/Shanghai][u-ca=chinese]");
+
+if (
+  inferredType.name === "string" &&
+  inferredType.format.name === "datetime" &&
+  inferredType.format.variant === "rfc3339" &&
+  inferredType.format.extensions.includes("timezone")
+) {
+  const zonedDateTime = Temporal.ZonedDateTime.from(inferredType.value);
+  // Temporal.ZonedDateTime <2022-02-28T11:06:00.092121729+08:00[Asia/Shanghai][u-ca=chinese]>
+}
+```
+
 JSON Infer Types also supports unix epoch timestamps
 
 ```js

src/formats/datetime.ts

@@ -1,7 +1,10 @@
+type Rfc3339Extensions = Array<"timezone" | "calendar"> | undefined;
+
 export type JSONDateTimeFormat = {
   name: "datetime";
   parts: "datetime" | "date" | "time";
   variant: "rfc2822" | "rfc3339";
+  extensions?: Rfc3339Extensions;
 };
 
 export function inferDatetime(value: string): JSONDateTimeFormat | undefined {
@@ -21,33 +24,37 @@ export function inferDatetime(value: string): JSONDateTimeFormat | undefined {
 }
 
 const rfc3339WithYmd =
-  /^([+-]\d{6}|\d{4})(?:-?(\d\d)(?:-?(\d\d))?)?(?:[T\s](\d\d)(?::?(\d\d)(?::?(\d\d)(?:[.,](\d{1,30}))?)?)?(?:(Z?)|([+-]\d\d)(?::?(\d\d))?))?$/;
+  /^([+-]\d{6}|\d{4})(?:-?(\d\d)(?:-?(\d\d))?)?(?:[T\s](\d\d)(?::?(\d\d)(?::?(\d\d)(?:[.,](\d{1,30}))?)?)?(?:(Z?)|([+-]\d\d)(?::?(\d\d))?))?(?:\[([A-Za-z/_-]+)\])?(?:\[(u-ca=(?:buddhist|chinese|coptic|dangi|ethioaa|ethiopic|gregory|hebrew|indian|islamic|islamic-umalqura|islamic-tbla|islamic-civil|islamic-rgsa|islamicc|iso8601|japanese|persian|roc))\])?$/;
 
 const rfc3339WithWeekIndex =
-  /^(\d{4})-?W(\d\d)(?:-?(\d))?(?:[T\s](\d\d)(?::?(\d\d)(?::?(\d\d)(?:[.,](\d{1,30}))?)?)?(?:(Z?)|([+-]\d\d)(?::?(\d\d))?))?$/;
+  /^(\d{4})-?W(\d\d)(?:-?(\d))?(?:[T\s](\d\d)(?::?(\d\d)(?::?(\d\d)(?:[.,](\d{1,30}))?)?)?(?:(Z?)|([+-]\d\d)(?::?(\d\d))?))?(?:\[([A-Za-z/_-]+)\])?(?:\[(u-ca=(?:buddhist|chinese|coptic|dangi|ethioaa|ethiopic|gregory|hebrew|indian|islamic|islamic-umalqura|islamic-tbla|islamic-civil|islamic-rgsa|islamicc|iso8601|japanese|persian|roc))\])?$/;
 
 const rfc3339WithOrdinal =
-  /^(\d{4})-?(\d{3})?(?:[T\s](\d\d)(?::?(\d\d)(?::?(\d\d)(?:[.,](\d{1,30}))?)?)?(?:(Z?)|([+-]\d\d)(?::?(\d\d))?))?$/;
+  /^(\d{4})-?(\d{3})?(?:[T\s](\d\d)(?::?(\d\d)(?::?(\d\d)(?:[.,](\d{1,30}))?)?)?(?:(Z?)|([+-]\d\d)(?::?(\d\d))?))?(?:\[([A-Za-z/_-]+)\])?(?:\[(u-ca=(?:buddhist|chinese|coptic|dangi|ethioaa|ethiopic|gregory|hebrew|indian|islamic|islamic-umalqura|islamic-tbla|islamic-civil|islamic-rgsa|islamicc|iso8601|japanese|persian|roc))\])?$/;
 
 const rfc3339TimeOnly =
-  /^(?:(\d\d)(?::?(\d\d)(?::?(\d\d)(?:[.,](\d{1,30}))?)?)?(?:(Z?)|([+-]\d\d)(?::?(\d\d))?))?$/;
+  /^(?:(\d\d)(?::?(\d\d)(?::?(\d\d)(?:[.,](\d{1,30}))?)?)?(?:(Z?)|([+-]\d\d)(?::?(\d\d))?))?(?:\[([A-Za-z/_-]+)\])?(?:\[(u-ca=(?:buddhist|chinese|coptic|dangi|ethioaa|ethiopic|gregory|hebrew|indian|islamic|islamic-umalqura|islamic-tbla|islamic-civil|islamic-rgsa|islamicc|iso8601|japanese|persian|roc))\])?$/;
 
 const rfc3339 = [
   {
     matches: rfc3339WithYmd,
     parts: rfc3339Parts,
+    extensions: rfc3339Extensions(11, 12),
   },
   {
     matches: rfc3339WithWeekIndex,
     parts: rfc3339Parts,
+    extensions: rfc3339Extensions(11, 12),
   },
   {
     matches: rfc3339WithOrdinal,
     parts: rfc3339WithOrdinalParts,
+    extensions: rfc3339Extensions(10, 11),
   },
   {
     matches: rfc3339TimeOnly,
     parts: () => <const>"time",
+    extensions: rfc3339Extensions(8, 9),
   },
 ];
 
@@ -57,6 +64,7 @@ function inferRFC3339(value: string): JSONDateTimeFormat | undefined {
       return {
         matches: rfc.matches.exec(value),
         parts: rfc.parts,
+        extensions: rfc.extensions,
       };
     })
     .filter((rfc) => rfc.matches !== null && rfc.matches.some((i) => i));
@@ -72,6 +80,8 @@ function inferRFC3339(value: string): JSONDateTimeFormat | undefined {
       // eslint-disable-next-line @typescript-eslint/no-non-null-assertion
       parts: rfc3339BestMatch.parts(rfc3339BestMatch.matches!),
       variant: "rfc3339",
+      // eslint-disable-next-line @typescript-eslint/no-non-null-assertion
+      extensions: rfc3339BestMatch.extensions(rfc3339BestMatch.matches!),
     };
   }
 
@@ -92,6 +102,25 @@ function rfc3339Parts(match: RegExpMatchArray): "datetime" | "date" {
   return "date";
 }
 
+function rfc3339Extensions(
+  timezoneIndex = 11,
+  calendarIndex = 12,
+): (match: RegExpMatchArray) => Rfc3339Extensions {
+  return (match: RegExpMatchArray): Rfc3339Extensions => {
+    const extensions: Array<"timezone" | "calendar"> = [];
+
+    if (match[timezoneIndex] !== undefined) {
+      extensions.push("timezone");
+    }
+
+    if (match[calendarIndex] !== undefined) {
+      extensions.push("calendar");
+    }
+
+    return extensions.length > 0 ? extensions : undefined;
+  };
+}
+
 function rfc3339WithOrdinalParts(match: RegExpMatchArray): "datetime" | "date" {
   const dateParts = [1, 2];
   const timeParts = [3, 4, 5, 6];

tests/stringFormats.test.ts

@@ -27,6 +27,46 @@ describe("rfc3339", () => {
     });
   });
 
+  test.each([
+    "2007-12-03T10:15:30+01:00[Europe/Paris]",
+    "2016-05-25T09:08:34.123[America/North_Dakota/Beulah]",
+    "2016-W21-3T09:24:15.123Z[America/Phoenix]",
+    "1983-10-14T13:30Z[Europe/Isle_of_Man]",
+    "2022-02-28T11:06:00.092121729+08:00[Asia/Shanghai]",
+  ])("%p should be inferred as an rfc3339 datetime with timezone extension", (value) => {
+    expect(inferType(value)).toEqual({
+      name: "string",
+      value,
+      format: {
+        name: "datetime",
+        parts: "datetime",
+        variant: "rfc3339",
+        extensions: ["timezone"],
+      },
+    });
+  });
+
+  test.each([
+    "2007-12-03T10:15:30+01:00[Europe/Paris][u-ca=hebrew]",
+    "2016-05-25T09:08:34.123[America/North_Dakota/Beulah][u-ca=iso8601]",
+    "2016-W21-3T09:24:15.123Z[America/Phoenix][u-ca=buddhist]",
+    "1983-10-14T13:30Z[Europe/Isle_of_Man][u-ca=japanese]",
+  ])(
+    "%p should be inferred as an rfc3339 datetime with timezone and calendar extension",
+    (value) => {
+      expect(inferType(value)).toEqual({
+        name: "string",
+        value,
+        format: {
+          name: "datetime",
+          parts: "datetime",
+          variant: "rfc3339",
+          extensions: ["timezone", "calendar"],
+        },
+      });
+    },
+  );
+
   test.each(["2016-05", "2016-05-25", "+002016-05-25", "2016-W21", "2016-W21-3", "2016-200"])(
     "%p should be inferred as an rfc3339 date",
     (value) => {
@@ -42,6 +82,26 @@ describe("rfc3339", () => {
     },
   );
 
+  test.each([
+    "2016-05[Europe/Paris][u-ca=hebrew]",
+    "2016-05-25[Europe/Isle_of_Man][u-ca=japanese]",
+    "+002016-05-25[America/Phoenix][u-ca=buddhist]",
+    "2016-W21[America/Phoenix][u-ca=buddhist]",
+    "2016-W21-3[America/Phoenix][u-ca=buddhist]",
+    "2016-200[America/Phoenix][u-ca=buddhist]",
+  ])("%p should be inferred as an rfc3339 date with timezone and calendar extensions", (value) => {
+    expect(inferType(value)).toEqual({
+      name: "string",
+      value,
+      format: {
+        name: "datetime",
+        parts: "date",
+        variant: "rfc3339",
+        extensions: ["timezone", "calendar"],
+      },
+    });
+  });
+
   test.each(["09:24:15.123Z", "09:24:15", "09:24"])(
     "%p should be inferred as an rfc3339 time",
     (value) => {
@@ -56,6 +116,23 @@ describe("rfc3339", () => {
       });
     },
   );
+
+  test.each([
+    "09:24:15.123Z[Europe/Isle_of_Man][u-ca=japanese]",
+    "09:24:15[America/Phoenix][u-ca=buddhist]",
+    "09:24[Europe/Paris][u-ca=hebrew]",
+  ])("%p should be inferred as an rfc3339 time with timezone and calendar extensions", (value) => {
+    expect(inferType(value)).toEqual({
+      name: "string",
+      value,
+      format: {
+        name: "datetime",
+        parts: "time",
+        variant: "rfc3339",
+        extensions: ["timezone", "calendar"],
+      },
+    });
+  });
 });
 
 describe("rfc2822", () => {