Fixed 7478: splitLines keepEol option (#8621)

This commit is contained in:
Iván Montes 2018-08-13 11:42:50 +02:00 • committed by Andreas Rumpf
commit ee29370f60
2 changed files with 29 additions and 13 deletions

View file

@ -624,12 +624,13 @@ iterator rsplit*(s: string, sep: string, maxsplit: int = -1,
## Substrings are separated from the right by the string `sep` ## Substrings are separated from the right by the string `sep`
rsplitCommon(s, sep, maxsplit, sep.len) rsplitCommon(s, sep, maxsplit, sep.len)
iterator splitLines*(s: string): string = iterator splitLines*(s: string, keepEol = false): string =
## Splits the string `s` into its containing lines. ## Splits the string `s` into its containing lines.
## ##
## Every `character literal <manual.html#character-literals>`_ newline ## Every `character literal <manual.html#character-literals>`_ newline
## combination (CR, LF, CR-LF) is supported. The result strings contain no ## combination (CR, LF, CR-LF) is supported. The result strings contain no
## trailing ``\n``. ## trailing end of line characters unless parameter ``keepEol`` is set to
## ``true``.
## ##
## Example: ## Example:
## ##
@ -649,22 +650,30 @@ iterator splitLines*(s: string): string =
## "" ## ""
var first = 0 var first = 0
var last = 0 var last = 0
var eolpos = 0
while true: while true:
while last < s.len and s[last] notin {'\c', '\l'}: inc(last) while last < s.len and s[last] notin {'\c', '\l'}: inc(last)
yield substr(s, first, last-1)
# skip newlines: eolpos = last
if last >= s.len: break if last < s.len:
if s[last] == '\l': inc(last) if s[last] == '\l': inc(last)
elif s[last] == '\c': elif s[last] == '\c':
inc(last) inc(last)
if last < s.len and s[last] == '\l': inc(last) if last < s.len and s[last] == '\l': inc(last)
yield substr(s, first, if keepEol: last-1 else: eolpos-1)
# no eol characters consumed means that the string is over
if eolpos == last:
break
first = last first = last
proc splitLines*(s: string): seq[string] {.noSideEffect, proc splitLines*(s: string, keepEol = false): seq[string] {.noSideEffect,
rtl, extern: "nsuSplitLines".} = rtl, extern: "nsuSplitLines".} =
## The same as the `splitLines <#splitLines.i,string>`_ iterator, but is a ## The same as the `splitLines <#splitLines.i,string>`_ iterator, but is a
## proc that returns a sequence of substrings. ## proc that returns a sequence of substrings.
accumulateResult(splitLines(s)) accumulateResult(splitLines(s, keepEol=keepEol))
proc countLines*(s: string): int {.noSideEffect, proc countLines*(s: string): int {.noSideEffect,
rtl, extern: "nsuCountLines".} = rtl, extern: "nsuCountLines".} =

View file

@ -199,6 +199,12 @@ proc testRFind =
assert "0123456789ABCDEFGAH".rfind({'A'..'C'}, 13) == 12 assert "0123456789ABCDEFGAH".rfind({'A'..'C'}, 13) == 12
assert "0123456789ABCDEFGAH".rfind({'G'..'H'}, 13) == -1 assert "0123456789ABCDEFGAH".rfind({'G'..'H'}, 13) == -1
proc testSplitLines() =
let fixture = "a\nb\rc\r\nd"
assert len(fixture.splitLines) == 4
assert splitLines(fixture) == @["a", "b", "c", "d"]
assert splitLines(fixture, keepEol=true) == @["a\n", "b\r", "c\r\n", "d"]
proc testCountLines = proc testCountLines =
proc assertCountLines(s: string) = assert s.countLines == s.splitLines.len proc assertCountLines(s: string) = assert s.countLines == s.splitLines.len
assertCountLines("") assertCountLines("")
@ -252,6 +258,7 @@ proc testParseInts =
testDelete() testDelete()
testFind() testFind()
testRFind() testRFind()
testSplitLines()
testCountLines() testCountLines()
testParseInts() testParseInts()