Strutils new sets

changelog.md

@@ -337,6 +337,8 @@
 
 - Added `dom.scrollIntoView` proc with options
 
+- Added `ControlChars`, `GraphicChars`, `PrintableChars`, and `Punctuation` sets to `strutils`.
+
 ## Language changes
 
 - `nimscript` now handles `except Exception as e`.

lib/pure/strutils.nim

@@ -84,7 +84,7 @@ from std/private/strimpl import cmpIgnoreStyleImpl, cmpIgnoreCaseImpl, startsWit
 
 
 const
-  Whitespace* = {' ', '\t', '\v', '\r', '\l', '\f'}
+  Whitespace* = {' ', '\t', '\v', '\r', '\n', '\f'}
     ## All the characters that count as whitespace (space, tab, vertical tab,
     ## carriage return, new line, form feed).
 
@@ -94,21 +94,33 @@ const
   Digits* = {'0'..'9'}
     ## The set of digits.
 
-  HexDigits* = {'0'..'9', 'A'..'F', 'a'..'f'}
+  HexDigits* = Digits + {'A'..'F', 'a'..'f'}
     ## The set of hexadecimal digits.
 
-  IdentChars* = {'a'..'z', 'A'..'Z', '0'..'9', '_'}
+  IdentChars* = Letters + Digits + {'_'}
     ## The set of characters an identifier can consist of.
 
-  IdentStartChars* = {'a'..'z', 'A'..'Z', '_'}
+  IdentStartChars* = Letters + {'_'}
     ## The set of characters an identifier can start with.
 
-  Newlines* = {'\13', '\10'}
-    ## The set of characters a newline terminator can start with (carriage
-    ## return, line feed).
+  Newlines* = {'\r', '\n'}
+    ## The set of characters a newline terminator can consist of
+
+  ControlChars* = {'\0'..'\31', '\127'}
+    ## The set of all ASCII control characters.
+
+  GraphicChars* = {'!'..'~'}
+    ## The set of all ASCII graphic characters.
+
+  PrintableChars* = GraphicChars + {' '}
+    ## The set of all ASCII printable characters.
+
+  Punctuation* = {'!', '\"', '#', '$', '%', '&', '\'', '(', ')', '*', '+', ',', '-', '.', '/', ':', ';', '<', '=', '>', '?', '@', '[', '\\', ']', '^', '_', '`', '{', '|', '}', '~'}
+    ## The set of all ASCII punctuation characters.
+    ## Is the same as `PrintableChars - Letters - Digits`
 
   AllChars* = {'\x00'..'\xFF'}
-    ## A set with all the possible characters.
+    ## The set of all characters.
     ##
     ## Not very useful by its own, you can use it to create *inverted* sets to
     ## make the `find func<#find,string,set[char],Natural,int>`_
@@ -185,7 +197,6 @@ func isUpperAscii*(c: char): bool {.rtl, extern: "nsuIsUpperAsciiChar".} =
     doAssert isUpperAscii('7') == false
   return c in {'A'..'Z'}
 
-
 func toLowerAscii*(c: char): char {.rtl, extern: "nsuToLowerAsciiChar".} =
   ## Returns the lower case version of character `c`.
   ##

tests/stdlib/tstrutils.nim

@@ -13,6 +13,33 @@ template rejectParse(e) =
   except ValueError: discard
 
 template main() =
+  # Tests for the sets
+
+  block: # Whitespace
+    proc isspace(c: cint): cint {.importc, header: "<ctype.h>".}
+    for i in char.low .. char.high:
+      doAssert (isspace(i.cint) > 0) == (i in Whitespace)
+
+  block: # ControlChars
+    proc iscntrl(c: cint): cint {.importc, header: "<ctype.h>".}
+    for i in char.low .. char.high:
+      doAssert (iscntrl(i.cint) > 0) == (i in ControlChars)
+
+  block: # GraphicChars
+    proc isgraph(c: cint): cint {.importc, header: "<ctype.h>".}
+    for i in char.low .. char.high:
+      doAssert (isgraph(i.cint) > 0) == (i in GraphicChars)
+
+  block: # PrintableChars
+    proc isprint(c: cint): cint {.importc, header: "<ctype.h>".}
+    for i in char.low .. char.high:
+      doAssert (isprint(i.cint) > 0) == (i in PrintableChars)
+
+  block: # Punctuation
+    proc ispunct(c: cint): cint {.importc, header: "<ctype.h>".}
+    for i in char.low .. char.high:
+      doAssert (ispunct(i.cint) > 0) == (i in Punctuation)
+
   block: # strip
     doAssert strip("  ha  ") == "ha"
     doAssert strip("  foofoofoo  ") == "foofoofoo"