Data analysts should be able to use Text.to_case to change the case…

… of Text values (#3302)

* Move to_upper_case and to_lower_case into to_case

* Add an export, not sure about it

* Implement title case

TODO: some more tests would be good

* Add more tests

* explain title case

* fix todo

* changelog

CHANGELOG.md

@@ -55,6 +55,8 @@
   functions][3287]
 - [Implemented new `Text.starts_with` and `Text.ends_with` functions, replacing
   existing functions][3292]
+- [Implemented `Text.to_case`, replacing `Text.to_lower_case` and
+  `Text.to_upper_case`][3302]
 
 [debug-shortcuts]:
   https://github.com/enso-org/enso/blob/develop/app/gui/docs/product/shortcuts.md#debug
@@ -85,6 +87,7 @@
 [3285]: https://github.com/enso-org/enso/pull/3285
 [3287]: https://github.com/enso-org/enso/pull/3287
 [3292]: https://github.com/enso-org/enso/pull/3292
+[3302]: https://github.com/enso-org/enso/pull/3302
 
 #### Enso Compiler
 

distribution/lib/Standard/Base/0.0.0-dev/src/Data/Text/Case.enso

@@ -0,0 +1,10 @@
+## Specifies the casing options for text conversion.
+type Case
+    ## All letters in lower case.
+    type Lower
+
+    ## All letters in upper case.
+    type Upper
+
+    ## First letter of each word in upper case, rest in lower case.
+    type Title

distribution/lib/Standard/Base/0.0.0-dev/src/Data/Text/Extensions.enso

@@ -5,6 +5,7 @@ from Standard.Builtins import Text, Prim_Text_Helpers
 
 import Standard.Base.Data.Text.Regex
 import Standard.Base.Data.Text.Regex.Mode
+import Standard.Base.Data.Text.Case
 import Standard.Base.Data.Text.Line_Ending_Style
 import Standard.Base.Data.Text.Split_Kind
 import Standard.Base.Data.Text.Text_Sub_Range
@@ -13,6 +14,7 @@ import Standard.Base.Meta
 
 from Standard.Builtins export Text
 
+export Standard.Base.Data.Text.Case
 export Standard.Base.Data.Text.Split_Kind
 export Standard.Base.Data.Text.Line_Ending_Style
 
@@ -551,7 +553,7 @@ Text.equals_ignore_case that locale=Locale.default =
    used to perform case-insensitive comparisons.
 Text.to_case_insensitive_key : Locale -> Text
 Text.to_case_insensitive_key locale=Locale.default =
-    this.to_lower_case locale . to_upper_case locale
+    this.to_case Case.Lower locale . to_case Case.Upper locale
 
 ## Compare two texts to discover their ordering.
 
@@ -984,40 +986,11 @@ Text.drop range =
         if char_range.end == (Text_Utils.char_length this) then prefix else
             prefix + Text_Utils.drop_first this char_range.end
 
-## ALIAS Lower Case
-
-   Converts each character in `this` to lower case.
-
-   Arguments:
-   - locale: specifies the locale for character case mapping. Defaults to the
-     `Locale.default` locale.
-
-   ! What is a Character?
-     A character is defined as an Extended Grapheme Cluster, see Unicode
-     Standard Annex 29. This is the smallest unit that still has semantic
-     meaning in most text-processing applications.
-
-   > Example
-     Converting a text to lower case in the default locale:
-
-         "My TeXt!".to_lower_case == "my text!"
-
-   > Example
-     Converting a text to lower case in a specified locale (here, Turkey):
-
-         from Standard.Base import all
-         import Standard.Base.Data.Locale
-
-         example_case_with_locale = "I".to_lower_case (Locale.new "tr") == "ı"
-Text.to_lower_case : Locale.Locale -> Text
-Text.to_lower_case locale=Locale.default =
-    UCharacter.toLowerCase locale.java_locale this
-
-## ALIAS Upper Case
-
-   Converts each character in `this` to upper case.
+## ALIAS lower, upper, title, proper
+   Converts each character in `this` to the specified case.
 
    Arguments:
+   - case_option: specifies how to convert the characters.
    - locale: specifies the locale for character case mapping. Defaults to
      `Locale.default`.
 
@@ -1026,18 +999,26 @@ Text.to_lower_case locale=Locale.default =
      Standard Annex 29. This is the smallest unit that still has semantic
      meaning in most text-processing applications.
 
+   ! What is title case?
+     Title case capitalizes the first letter of every word and ensures that all
+     the remaining letters are in lower case. Some definitions of title case
+     avoid capitalizing minor words (like the article "the" in English) but this
+     implementation treats all words in the same way.
+
    > Example
-     Converting a text to upper case in the default locale:
+     Converting a text to lower case in the default locale:
 
-         "My TeXt!".to_upper_case == "MY TEXT!"
+         "My TeXt!".to_case == "my text!"
 
    > Example
      Converting a text to upper case in a specified locale:
 
          from Standard.Base import all
          import Standard.Base.Data.Locale
 
-         example_case_with_locale = "i".to_upper_case (Locale.new "tr") == "İ"
-Text.to_upper_case : Locale.Locale -> Text
-Text.to_upper_case locale=Locale.default =
-    UCharacter.toUpperCase locale.java_locale this
+         example_case_with_locale = "i".to_case Upper (Locale.new "tr") == "İ"
+Text.to_case : Case -> Locale -> Text
+Text.to_case case_option=Case.Lower locale=Locale.Default = case case_option of
+    Case.Lower -> UCharacter.toLowerCase locale.java_locale this
+    Case.Upper -> UCharacter.toUpperCase locale.java_locale this
+    Case.Title -> UCharacter.toTitleCase locale.java_locale this Nothing

distribution/lib/Standard/Base/0.0.0-dev/src/Main.enso

@@ -47,7 +47,14 @@ from project.Data.Number.Extensions export all hiding Math, String, Double
 from project.Data.Noise export all hiding Noise
 from project.Data.Pair export Pair
 from project.Data.Range export Range
-from project.Data.Text.Extensions export Text, Split_Kind, Line_Ending_Style
+## TODO [RW] Once autoscoping is implemented or automatic imports for ADTs are
+   fixed in the IDE, we should revisit if we want to export ADTs like `Case` by
+   default. It may be unnecessary pollution of scope, but until the issues are
+   fixed, common standard library functions are almost unusable in the GUI.
+   Relevant issues:
+   https://www.pivotaltracker.com/story/show/181403340
+   https://www.pivotaltracker.com/story/show/181309938
+from project.Data.Text.Extensions export Text, Split_Kind, Line_Ending_Style, Case
 from project.Data.Text.Matching export Case_Insensitive, Text_Matcher, Regex_Matcher
 from project.Error.Common export all
 from project.Error.Extensions export all

distribution/lib/Standard/Table/0.0.0-dev/src/Data/Table.enso

@@ -218,7 +218,7 @@ type Table
        representation for this table.
     default_visualization : Visualization.Id.Id
     default_visualization =
-        cols = this.columns.map .name . map .to_lower_case
+        cols = this.columns.map .name . map name-> name.to_case Case.Lower
         if cols.contains "latitude" && cols.contains "longitude" then Visualization.Id.geo_map else
             if cols.contains "x" && cols.contains "y" then Visualization.Id.scatter_plot else
                 Visualization.Id.table

distribution/lib/Standard/Visualization/0.0.0-dev/src/Scatter_Plot.enso

@@ -64,7 +64,7 @@ type PointData
 
     ## PRIVATE
     name : Text
-    name = this.to_text.to_lower_case
+    name = this.to_text.to_case Case.Lower
 
     ## PRIVATE
     fallback_column : Table -> Column ! No_Fallback_Column

test/Tests/src/Data/Text_Spec.enso

@@ -300,12 +300,34 @@ spec =
             '✨🚀🚧😍😃😍😎😙😉☺'.drop (Range -3 -1) . should_equal '✨🚀🚧😍😃😍😎☺'
 
         Test.specify "should correctly convert character case" <|
-            "FooBar Baz".to_lower_case.should_equal "foobar baz"
-            "FooBar Baz".to_upper_case.should_equal "FOOBAR BAZ"
-            "i".to_upper_case . should_equal "I"
-            "I".to_lower_case . should_equal "i"
-            "i".to_upper_case (Locale.new "tr") . should_equal "İ"
-            "I".to_lower_case (Locale.new "tr") . should_equal "ı"
+            "FooBar Baz".to_case Case.Lower . should_equal "foobar baz"
+            "FooBar Baz".to_case Case.Upper . should_equal "FOOBAR BAZ"
+
+            "foo bar baz".to_case Case.Title . should_equal "Foo Bar Baz"
+            "foo-bar, baz.baz foo_foo".to_case Case.Title . should_equal "Foo-Bar, Baz.baz Foo_foo"
+            "jAck the rippER".to_case Case.Title (Locale.uk) . should_equal "Jack The Ripper"
+
+            "i".to_case Case.Upper . should_equal "I"
+            "I".to_case Case.Lower . should_equal "i"
+            "i".to_case Case.Upper (Locale.new "tr") . should_equal "İ"
+            "I".to_case Case.Lower (Locale.new "tr") . should_equal "ı"
+            "İ".to_case Case.Lower . should_equal "i̇"
+            "ı".to_case Case.Upper . should_equal "I"
+
+            "Straße".to_case Case.Upper . should_equal "STRASSE"
+            "STRASSE".to_case Case.Lower . should_equal "strasse"
+            "et cætera".to_case Case.Upper . should_equal "ET CÆTERA"
+            ("β".to_case Case.Upper == "B") . should_be_false
+            "δλφξ".to_case Case.Upper . should_equal "ΔΛΦΞ"
+            "ΔΛΦΞ".to_case Case.Lower . should_equal "δλφξ"
+            "δλ φξ".to_case Case.Title . should_equal "Δλ Φξ"
+
+            '✨🚀🚧😍😃😎😙😉☺'.to_case Case.Upper . should_equal '✨🚀🚧😍😃😎😙😉☺'
+            '✨🚀🚧😍😃😎😙😉☺'.to_case Case.Lower . should_equal '✨🚀🚧😍😃😎😙😉☺'
+            '✨🚀🚧😍😃😎😙😉☺'.to_case Case.Title . should_equal '✨🚀🚧😍😃😎😙😉☺'
+
+            "123".to_case Case.Upper . should_equal "123"
+            "abc123".to_case Case.Upper . should_equal "ABC123"
 
         Test.specify "should dump utf-16 characters to a vector" <|
             kshi_chars = kshi.utf_16