Excel_Workbook.read_many (#9759)

- Some minor linting fixes. - Adjust `headers` parameter so a dedicated type. ![image](https://github.com/enso-org/enso/assets/4699705/989f464d-df95-410e-a03b-36661f1c4a37) - Fix bug with `read` on an `Excel_Workbook` so error handled more gracefully and not panicking to UI. ![image](https://github.com/enso-org/enso/assets/4699705/23b4575f-daad-4719-a5cc-30d064bd7f7a) - Fix bug when writing to a file with an `Excel_Format` with an invalid extension which was causing a panic. ![image](https://github.com/enso-org/enso/assets/4699705/dc0e055c-c1b6-482f-b129-eb69f6554d72) - Add `read_many` to `Excel_Workbook` allowing reading more than one sheet at a time.
enso-org · Apr 24, 2024 · fb9cf38 · fb9cf38
1 parent 717f6bb
commit fb9cf38
Show file tree

Hide file tree

Showing 20 changed files with 262 additions and 105 deletions.
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -655,6 +655,8 @@
 - [Added `recursive` option to `File.delete`.][9719]
 - [Added `Vector.build`.][9725]
 - [Added `Table.running` method][9577]
+- [Added `Excel_Workbook.read_many` allowing reading more than one sheet at a
+  time.][9759]
 
 [debug-shortcuts]:
   https://github.com/enso-org/enso/blob/develop/app/gui/docs/product/shortcuts.md#debug
@@ -959,6 +961,7 @@
 [9716]: https://github.com/enso-org/enso/pull/9716
 [9719]: https://github.com/enso-org/enso/pull/9719
 [9725]: https://github.com/enso-org/enso/pull/9725
+[9759]: https://github.com/enso-org/enso/pull/9759
 [9577]: https://github.com/enso-org/enso/pull/9577
 
 #### Enso Compiler

diff --git a/distribution/lib/Standard/AWS/0.0.0-dev/src/S3/S3_File.enso b/distribution/lib/Standard/AWS/0.0.0-dev/src/S3/S3_File.enso
@@ -76,19 +76,19 @@ type S3_File
             content_length = translate_file_errors self <| S3.raw_head self.s3_path.bucket self.s3_path.key self.credentials . contentLength
             if content_length.is_nothing then Error.throw (S3_Error.Error "ContentLength header is missing." self.uri) else content_length
 
-    ## ICON folder_add
-       GROUP Output
+    ## GROUP Output
+       ICON folder_add
        Creates the directory represented by this file if it did not exist.
 
        It also creates parent directories if they did not exist.
 
        ? S3 Handling of Directories
 
-         S3 does not have a native concept of directories.
-         TODO: Add more information about how S3 handles directories.
-         https://github.com/enso-org/enso/issues/9704
+       S3 does not have a native concept of directories.
     create_directory : File
     create_directory self =
+        ## TODO Add more information about how S3 handles directories.
+           https://github.com/enso-org/enso/issues/9704
         Unimplemented.throw "Creating S3 folders is currently not implemented."
 
     ## PRIVATE

diff --git a/distribution/lib/Standard/Base/0.0.0-dev/src/Enso_Cloud/Enso_File.enso b/distribution/lib/Standard/Base/0.0.0-dev/src/Enso_Cloud/Enso_File.enso
@@ -40,10 +40,10 @@ import project.System.Output_Stream.Output_Stream
 from project.Data.Boolean import Boolean, False, True
 from project.Data.Index_Sub_Range.Index_Sub_Range import Last
 from project.Data.Text.Extensions import all
-from project.Enso_Cloud.Public_Utils import get_required_field
 from project.Enso_Cloud.Internal.Enso_File_Helpers import all
-from project.System.File_Format import Auto_Detect, Bytes, File_Format, Plain_Text_Format
+from project.Enso_Cloud.Public_Utils import get_required_field
 from project.System.File import find_extension_from_name
+from project.System.File_Format import Auto_Detect, Bytes, File_Format, Plain_Text_Format
 from project.System.File.Generic.File_Write_Strategy import generic_copy
 
 type Enso_File
@@ -310,8 +310,8 @@ type Enso_File
             Asset_Cache.update file asset
             file
 
-    ## ICON folder_add
-       GROUP Output
+    ## GROUP Output
+       ICON folder_add
        Creates the directory represented by this file if it did not exist.
 
        It also creates parent directories if they did not exist.

diff --git a/distribution/lib/Standard/Base/0.0.0-dev/src/Enso_Cloud/Internal/Enso_File_Helpers.enso b/distribution/lib/Standard/Base/0.0.0-dev/src/Enso_Cloud/Internal/Enso_File_Helpers.enso
@@ -4,8 +4,8 @@ import project.Data.Json.JS_Object
 import project.Enso_Cloud.Enso_File.Enso_Asset_Type
 import project.Enso_Cloud.Enso_File.Enso_File
 import project.Enso_Cloud.Errors.Enso_Cloud_Error
-import project.Enso_Cloud.Internal.Existing_Enso_Asset.Existing_Enso_Asset
 import project.Enso_Cloud.Internal.Existing_Enso_Asset.Asset_Cache
+import project.Enso_Cloud.Internal.Existing_Enso_Asset.Existing_Enso_Asset
 import project.Enso_Cloud.Internal.Utils
 import project.Error.Error
 import project.Errors.File_Error.File_Error

diff --git a/distribution/lib/Standard/Base/0.0.0-dev/src/System/File.enso b/distribution/lib/Standard/Base/0.0.0-dev/src/System/File.enso
@@ -495,8 +495,8 @@ type File
     is_directory : Boolean
     is_directory self = @Builtin_Method "File.is_directory"
 
-    ## ICON folder_add
-       GROUP Output
+    ## GROUP Output
+       ICON folder_add
        Creates the directory represented by this file if it did not exist.
 
        It also creates parent directories if they did not exist.

diff --git a/distribution/lib/Standard/Table/0.0.0-dev/src/Delimited/Delimited_Format.enso b/distribution/lib/Standard/Table/0.0.0-dev/src/Delimited/Delimited_Format.enso
@@ -10,6 +10,7 @@ from Standard.Base.Widget_Helpers import make_file_read_delimiter_selector
 
 import project.Data_Formatter.Data_Formatter
 import project.Delimited.Quote_Style.Quote_Style
+import project.Headers.Headers
 import project.Internal.Delimited_Reader
 import project.Internal.Delimited_Writer
 import project.Match_Columns.Match_Columns
@@ -35,12 +36,10 @@ type Delimited_Format
          does not include the header row (if applicable).
        - quote_style: Specifies the style of quotes used for reading and
          writing.
-       - headers: If set to `True`, the first row is used as column names. If
-         set to `False`, the column names are generated by adding increasing
-         numeric suffixes to the base name `Column` (i.e. `Column_1`,
-         `Column_2` etc.). If set to `Infer`, the process tries to infer if
-         headers are present on the first row. If the column names are not
-         unique, numeric suffixes will be appended to disambiguate them.
+       - headers: Specifies if the first row contains the  column names. If set
+         to `Detect_Headers`, the process tries to infer if headers are
+         present. If the column names are not unique, numeric suffixes will be
+         appended to disambiguate them.
        - value_formatter: Formatter to parse text values into numbers, dates,
          times, etc. If `Nothing` values are left as Text.
        - keep_invalid_rows: Specifies whether rows that contain less or more
@@ -58,7 +57,7 @@ type Delimited_Format
          defaults to `Nothing` which means that comments are disabled.
     @delimiter make_file_read_delimiter_selector
     @encoding Encoding.default_widget
-    Delimited (delimiter:Text=',') (encoding:Encoding=Encoding.utf_8) (skip_rows:Integer=0) (row_limit:Integer|Nothing=Nothing) (quote_style:Quote_Style=Quote_Style.With_Quotes) (headers:Boolean|Infer=Infer) (value_formatter:Data_Formatter|Nothing=Data_Formatter.Value) (keep_invalid_rows:Boolean=True) (line_endings:Line_Ending_Style|Infer=Infer) (comment_character:Text|Nothing=Nothing)
+    Delimited (delimiter:Text=',') (encoding:Encoding=Encoding.utf_8) (skip_rows:Integer=0) (row_limit:Integer|Nothing=Nothing) (quote_style:Quote_Style=Quote_Style.With_Quotes) (headers:Headers=Headers.Detect_Headers) (value_formatter:Data_Formatter|Nothing=Data_Formatter.Value) (keep_invalid_rows:Boolean=True) (line_endings:Line_Ending_Style|Infer=Infer) (comment_character:Text|Nothing=Nothing)
 
     ## PRIVATE
        ADVANCED
@@ -112,8 +111,8 @@ type Delimited_Format
     ## PRIVATE
        Clone the instance with some properties overridden.
        Note: This function is internal until such time as Atom cloning with modification is built into Enso.
-    clone : Quote_Style -> (Boolean|Infer) -> (Data_Formatter|Nothing) -> Boolean -> (Text|Nothing) -> (Text|Nothing) -> Delimited_Format
-    clone self (quote_style=self.quote_style) (headers=self.headers) (value_formatter=self.value_formatter) (keep_invalid_rows=self.keep_invalid_rows) (line_endings=self.line_endings) (comment_character=self.comment_character) =
+    clone : Quote_Style -> Headers -> (Data_Formatter|Nothing) -> Boolean -> (Text|Nothing) -> (Text|Nothing) -> Delimited_Format
+    clone self (quote_style=self.quote_style) (headers:Headers=self.headers) (value_formatter=self.value_formatter) (keep_invalid_rows=self.keep_invalid_rows) (line_endings=self.line_endings) (comment_character=self.comment_character) =
         Delimited_Format.Delimited self.delimiter self.encoding self.skip_rows self.row_limit quote_style headers value_formatter keep_invalid_rows line_endings comment_character
 
     ## ICON data_input
@@ -131,13 +130,13 @@ type Delimited_Format
     ## ICON data_input
        Create a clone of this with first row treated as header.
     with_headers : Delimited_Format
-    with_headers self = self.clone headers=True
+    with_headers self = self.clone headers=Headers.Has_Headers
 
     ## ICON data_input
        Create a clone of this where the first row is treated as data, not a
        header.
     without_headers : Delimited_Format
-    without_headers self = self.clone headers=False
+    without_headers self = self.clone headers=Headers.No_Headers
 
     ## ICON data_input
        Create a clone of this with value parsing.

diff --git a/distribution/lib/Standard/Table/0.0.0-dev/src/Errors.enso b/distribution/lib/Standard/Table/0.0.0-dev/src/Errors.enso
@@ -247,13 +247,13 @@ type Unquoted_Characters_In_Output
 ## Indicates that a specified location was not valid.
 type Invalid_Location
     ## PRIVATE
-    Error (location : Text | Any)
+    Error (location : Text | Any) (message:Text|Nothing=Nothing)
 
     ## PRIVATE
        Pretty print the invalid location error.
     to_display_text : Text
     to_display_text self =
-        "The location '"+self.location.to_text+"' is not valid."
+        self.message.if_nothing ("The location '"+self.location.to_text+"' is not valid.")
 
 ## Indicates that some values did not match the expected datatype format.
 
@@ -278,22 +278,29 @@ type Empty_File_Error
     ## PRIVATE
        Pretty print the empty file error.
     to_display_text : Text
-    to_display_text = "It is not allowed to create a Table with no columns, so an empty file could not have been loaded."
+    to_display_text self =
+        _ = self
+        "The file is empty so it cannot be loaded."
 
     ## PRIVATE
     handle_java_exception =
         Panic.catch EmptyFileException handler=(_ -> Error.throw Empty_File_Error)
 
 ## Indicates that an empty sheet was encountered, so no data could be loaded.
-type Empty_Sheet_Error
+type Empty_Sheet
+    ## PRIVATE
+    Error
+
     ## PRIVATE
        Pretty print the empty sheet error.
     to_display_text : Text
-    to_display_text = "It is not allowed to create a Table with no columns, so an empty sheet could not have been loaded."
+    to_display_text self =
+        _ = self
+        "There is no data in the sheet."
 
     ## PRIVATE
     handle_java_exception =
-        Panic.catch EmptySheetException handler=(_ -> Error.throw Empty_Sheet_Error)
+        Panic.catch EmptySheetException handler=(_ -> Error.throw Empty_Sheet.Error)
 
 ## Indicates that the column was already present in the table.
 type Existing_Column

diff --git a/distribution/lib/Standard/Table/0.0.0-dev/src/Excel/Excel_Format.enso b/distribution/lib/Standard/Table/0.0.0-dev/src/Excel/Excel_Format.enso
@@ -10,6 +10,7 @@ from Standard.Base.System.File_Format import parse_boolean_with_infer
 
 import project.Excel.Excel_Range.Excel_Range
 import project.Excel.Excel_Workbook.Excel_Workbook
+import project.Headers.Headers
 import project.Internal.Excel_Reader
 import project.Internal.Excel_Section.Excel_Section
 import project.Internal.Excel_Writer
@@ -18,12 +19,12 @@ import project.Table.Table
 
 ## PRIVATE
    Resolve the xls_format setting to a boolean.
-should_treat_as_xls_format : (Boolean|Infer) -> File -> Boolean ! Illegal_Argument
-should_treat_as_xls_format xls_format file =
+should_treat_as_xls_format : (Boolean|Infer) -> File_Format_Metadata -> Boolean ! Illegal_Argument
+should_treat_as_xls_format xls_format file:File_Format_Metadata =
     if xls_format != Infer then xls_format else
         inferred_xls_format = xls_format_from_metadata file
         inferred_xls_format.if_nothing <|
-            Error.throw (Illegal_Argument.Error ("File not recognized as Excel file (" + file.name + ")"))
+            Error.throw (Illegal_Argument.Error ("File extension not recognized as Excel (" + file.name + "). Specify xls_format explicitly."))
 
 ## Read the file to a `Table` from an Excel file
 type Excel_Format
@@ -43,11 +44,10 @@ type Excel_Format
 
        Arguments:
        - sheet: The sheet number or name.
-       - headers: If set to `True`, the first row is used as column names. If
-         set to `False`, the column names are Excel column names. If set to
-         `Infer`, the process tries to infer if headers are present on the first
-          row. If the column names are not unique, numeric suffixes will be
-          appended to disambiguate them.
+       - headers: Specifies if the first row contains the  column names. If set
+         to `Detect_Headers`, the process tries to infer if headers are
+         present. If the column names are not unique, numeric suffixes will be
+         appended to disambiguate them.
        - skip_rows: The number of rows to skip before reading the data.
        - row_limit: The maximum number of rows to read. If set to `Nothing`, all
          rows are read.
@@ -56,17 +56,16 @@ type Excel_Format
          If set to `False`, the file is read as an Excel 2007+ format.
          `Infer` will attempt to deduce this from the extension of the filename.
     @sheet (Text_Input display=Display.Always)
-    Sheet (sheet:(Integer|Text)=1) (headers:(Boolean|Infer)=Infer) (skip_rows:Integer=0) (row_limit:(Integer|Nothing)=Nothing) (xls_format:Boolean|Infer=Infer)
+    Sheet (sheet:(Integer|Text)=1) (headers:Headers=Headers.Detect_Headers) (skip_rows:Integer=0) (row_limit:(Integer|Nothing)=Nothing) (xls_format:Boolean|Infer=Infer)
 
     ## Reads a range from an Excel file as a `Table`.
 
        Arguments:
        - address: A name of a range or an Excel-style address (e.g. Sheet1!A1:B2).
-       - headers: If set to `True`, the first row is used as column names. If
-         set to `False`, the column names are Excel column names. If set to
-         `Infer`, the process tries to infer if headers are present on the first
-          row. If the column names are not unique, numeric suffixes will be
-          appended to disambiguate them.
+       - headers: Specifies if the first row contains the  column names. If set
+         to `Detect_Headers`, the process tries to infer if headers are
+         present. If the column names are not unique, numeric suffixes will be
+         appended to disambiguate them.
        - skip_rows: The number of rows to skip before reading the data.
        - row_limit: The maximum number of rows to read. If set to `Nothing`, all
          rows are read.
@@ -75,7 +74,7 @@ type Excel_Format
          If set to `False`, the file is read as an Excel 2007+ format.
          `Infer` will attempt to deduce this from the extension of the filename.
     @address Text_Input
-    Range (address:(Text|Excel_Range)) (headers:(Boolean|Infer)=Infer) (skip_rows:Integer=0) (row_limit:(Integer|Nothing)=Nothing) (xls_format : Boolean | Infer = Infer)
+    Range (address:(Text|Excel_Range)) (headers:Headers=Headers.Detect_Headers) (skip_rows:Integer=0) (row_limit:(Integer|Nothing)=Nothing) (xls_format : Boolean | Infer = Infer)
 
     ## PRIVATE
        ADVANCED