jyapayne/Nim
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Added new proc

Browse source 
In reference to #2353
This commit is contained in:
apense 2015-07-03 21:33:12 -04:00
commit 64b3395ade
1 changed files with 18 additions and 10 deletions
Download patch file Download diff file Expand all files Collapse all files

28
lib/pure/unicode.nim
View file

@ -1163,7 +1163,7 @@ proc binarySearch(c: RuneImpl, tab: openArray[RuneImpl], len, stride: int): int
return -1 return -1
proc toLower*(c: Rune): Rune {.rtl, extern: "nuc$1", procvar.} = proc toLower*(c: Rune): Rune {.rtl, extern: "nuc$1", procvar.} =
## Converts `c` into lower case. This works for any Unicode character. ## Convert `c` into lower case. This works for any Unicode character.
## If possible, prefer `toLower` over `toUpper`. ## If possible, prefer `toLower` over `toUpper`.
var c = RuneImpl(c) var c = RuneImpl(c)
var p = binarySearch(c, tolowerRanges, len(tolowerRanges) div 3, 3) var p = binarySearch(c, tolowerRanges, len(tolowerRanges) div 3, 3)
@ -1175,7 +1175,7 @@ proc toLower*(c: Rune): Rune {.rtl, extern: "nuc$1", procvar.} =
return Rune(c) return Rune(c)
proc toUpper*(c: Rune): Rune {.rtl, extern: "nuc$1", procvar.} = proc toUpper*(c: Rune): Rune {.rtl, extern: "nuc$1", procvar.} =
## Converts `c` into upper case. This works for any Unicode character. ## Convert `c` into upper case. This works for any Unicode character.
## If possible, prefer `toLower` over `toUpper`. ## If possible, prefer `toLower` over `toUpper`.
var c = RuneImpl(c) var c = RuneImpl(c)
var p = binarySearch(c, toupperRanges, len(toupperRanges) div 3, 3) var p = binarySearch(c, toupperRanges, len(toupperRanges) div 3, 3)
@ -1194,7 +1194,7 @@ proc toTitle*(c: Rune): Rune {.rtl, extern: "nuc$1", procvar.} =
return Rune(c) return Rune(c)
proc isLower*(c: Rune): bool {.rtl, extern: "nuc$1", procvar.} = proc isLower*(c: Rune): bool {.rtl, extern: "nuc$1", procvar.} =
## returns true iff `c` is a lower case Unicode character ## Return true iff `c` is a lower case Unicode character.
## If possible, prefer `isLower` over `isUpper`. ## If possible, prefer `isLower` over `isUpper`.
var c = RuneImpl(c) var c = RuneImpl(c)
# Note: toUpperRanges is correct here! # Note: toUpperRanges is correct here!
@ -1206,7 +1206,7 @@ proc isLower*(c: Rune): bool {.rtl, extern: "nuc$1", procvar.} =
return true return true
proc isUpper*(c: Rune): bool {.rtl, extern: "nuc$1", procvar.} = proc isUpper*(c: Rune): bool {.rtl, extern: "nuc$1", procvar.} =
## returns true iff `c` is a upper case Unicode character ## Return true iff `c` is a upper case Unicode character.
## If possible, prefer `isLower` over `isUpper`. ## If possible, prefer `isLower` over `isUpper`.
var c = RuneImpl(c) var c = RuneImpl(c)
# Note: toLowerRanges is correct here! # Note: toLowerRanges is correct here!
@ -1218,7 +1218,7 @@ proc isUpper*(c: Rune): bool {.rtl, extern: "nuc$1", procvar.} =
return true return true
proc isAlpha*(c: Rune): bool {.rtl, extern: "nuc$1", procvar.} = proc isAlpha*(c: Rune): bool {.rtl, extern: "nuc$1", procvar.} =
## returns true iff `c` is an *alpha* Unicode character (i.e. a letter) ## Return true iff `c` is an *alpha* Unicode character (i.e., a letter)
if isUpper(c) or isLower(c): if isUpper(c) or isLower(c):
return true return true
var c = RuneImpl(c) var c = RuneImpl(c)
@ -1230,17 +1230,18 @@ proc isAlpha*(c: Rune): bool {.rtl, extern: "nuc$1", procvar.} =
return true return true
proc isTitle*(c: Rune): bool {.rtl, extern: "nuc$1", procvar.} = proc isTitle*(c: Rune): bool {.rtl, extern: "nuc$1", procvar.} =
## Return true iff `c` is a Unicode titlecase character
return isUpper(c) and isLower(c) return isUpper(c) and isLower(c)
proc isWhiteSpace*(c: Rune): bool {.rtl, extern: "nuc$1", procvar.} = proc isWhiteSpace*(c: Rune): bool {.rtl, extern: "nuc$1", procvar.} =
## returns true iff `c` is a Unicode whitespace character ## Return true iff `c` is a Unicode whitespace character
var c = RuneImpl(c) var c = RuneImpl(c)
var p = binarySearch(c, spaceRanges, len(spaceRanges) div 2, 2) var p = binarySearch(c, spaceRanges, len(spaceRanges) div 2, 2)
if p >= 0 and c >= spaceRanges[p] and c <= spaceRanges[p+1]: if p >= 0 and c >= spaceRanges[p] and c <= spaceRanges[p+1]:
return true return true
proc isCombining*(c: Rune): bool {.rtl, extern: "nuc$1", procvar.} = proc isCombining*(c: Rune): bool {.rtl, extern: "nuc$1", procvar.} =
## returns true iff `c` is a Unicode combining character ## Return true iff `c` is a Unicode combining character
var c = RuneImpl(c) var c = RuneImpl(c)
# Optimized to return false immediately for ASCII # Optimized to return false immediately for ASCII
@ -1251,7 +1252,7 @@ proc isCombining*(c: Rune): bool {.rtl, extern: "nuc$1", procvar.} =
(c >= 0xfe20 and c <= 0xfe2f)) (c >= 0xfe20 and c <= 0xfe2f))
iterator runes*(s: string): Rune = iterator runes*(s: string): Rune =
## iterates over any unicode character of the string `s`. ## Iterate over any unicode character of the string `s`
var var
i = 0 i = 0
result: Rune result: Rune
@ -1259,8 +1260,14 @@ iterator runes*(s: string): Rune =
fastRuneAt(s, i, result, true) fastRuneAt(s, i, result, true)
yield result yield result
proc runesIn*(s: string): seq[Rune] =
## Obtain a sequence containing the Runes in `s`
result = newSeq[Rune]()
for r in s.runes:
result.add(r)
proc cmpRunesIgnoreCase*(a, b: string): int {.rtl, extern: "nuc$1", procvar.} = proc cmpRunesIgnoreCase*(a, b: string): int {.rtl, extern: "nuc$1", procvar.} =
## compares two UTF8 strings and ignores the case. Returns: ## Compare two UTF8 strings and ignore the case. Returns:
## ##
## | 0 iff a == b ## | 0 iff a == b
## | < 0 iff a < b ## | < 0 iff a < b
@ -1277,7 +1284,7 @@ proc cmpRunesIgnoreCase*(a, b: string): int {.rtl, extern: "nuc$1", procvar.} =
result = a.len - b.len result = a.len - b.len
proc reversed*(s: string): string = proc reversed*(s: string): string =
## returns the reverse of `s`, interpreting it as unicode characters. Unicode ## Return the reverse of `s`, interpreting it as unicode characters. Unicode
## combining characters are correctly interpreted as well: ## combining characters are correctly interpreted as well:
## ##
## .. code-block:: nim ## .. code-block:: nim
@ -1322,3 +1329,4 @@ when isMainModule:
assert reversed("先秦兩漢") == "漢兩秦先" assert reversed("先秦兩漢") == "漢兩秦先"
assert reversed("as⃝df̅") == "f̅ds⃝a" assert reversed("as⃝df̅") == "f̅ds⃝a"
assert reversed("a⃞b⃞c⃞") == "c⃞b⃞a⃞" assert reversed("a⃞b⃞c⃞") == "c⃞b⃞a⃞"
assert len(runesIn("as⃝df̅")) == runeLen("as⃝df̅")