structure Unicode.UCDStreamextends String.Slice : Type

Stream type for Unicode Character Database (UCD) files

Unicode data files are semicolon ; (U+003B) separated fields, except for Unihan files and a few others that are tab (U+0009) separated. White spaces around field values are not significant. Line comments are prefixed with a number sign # (U+0023).

• str : String
• startInclusive : self.str.Pos
• endExclusive : self.str.Pos
• startInclusive_le_endExclusive : self.startInclusive ≤ self.endExclusive
• isUnihan : Bool

  isUnihan is true if the records are tab separated

def Unicode.instInhabitedUCDStream.default : UCDStream

Equations

• Unicode.instInhabitedUCDStream.default = { toSlice := default, isUnihan := default }

instance Unicode.instInhabitedUCDStream : Inhabited UCDStream

Equations

• Unicode.instInhabitedUCDStream = { default := Unicode.instInhabitedUCDStream.default }

def Unicode.UCDStream.ofStringSlice (str : String.Slice) : UCDStream

Make a UCDStream from a string slice

Equations

• Unicode.UCDStream.ofStringSlice str = { toSlice := str }

def Unicode.UCDStream.ofString (str : String) : UCDStream

Make a UCDStream from a string

Equations

• Unicode.UCDStream.ofString str = Unicode.UCDStream.ofStringSlice str.toSlice

def Unicode.UCDStream.ofSubstring (str : Substring.Raw) : UCDStream

Make a UCDStream from a substring

Equations

• Unicode.UCDStream.ofSubstring str = Unicode.UCDStream.ofStringSlice str.toString.toSlice

def Unicode.UCDStream.ofFile (path : System.FilePath) : IO UCDStream

Make a UCDStream from a file

Equations

• Unicode.UCDStream.ofFile path = Unicode.UCDStream.ofString <$> IO.FS.readFile path

partial def Unicode.UCDStream.nextLine? (stream : UCDStream) : Option (String.Slice × UCDStream)

Get the next line from the UCDStream

Line comments are stripped and blank lines are skipped.

def Unicode.UCDStream.next? (stream : UCDStream) : Option (Array String.Slice × UCDStream)

Get the next record from the UCDStream

Spaces around field values are trimmed.

Equations

• One or more equations did not get rendered due to their size.

instance Unicode.UCDStream.instStreamArraySlice : Std.Stream UCDStream (Array String.Slice)

Equations

• Unicode.UCDStream.instStreamArraySlice = { next? := Unicode.UCDStream.next? }