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

added maxsplit argument to strutils.split

Browse source
This commit is contained in:
Magnus Jöud 2015-10-14 13:44:20 +02:00
commit 739a8ea060
1 changed files with 25 additions and 10 deletions
Download patch file Download diff file Expand all files Collapse all files

33
lib/pure/strutils.nim
View file

@ -322,7 +322,7 @@ proc toOctal*(c: char): string {.noSideEffect, rtl, extern: "nsuToOctal".} =
result[i] = chr(val mod 8 + ord('0')) result[i] = chr(val mod 8 + ord('0'))
val = val div 8 val = val div 8
iterator split*(s: string, seps: set[char] = Whitespace): string = iterator split*(s: string, seps: set[char] = Whitespace, maxsplit: int = -1): string =
## Splits the string `s` into substrings using a group of separators. ## Splits the string `s` into substrings using a group of separators.
## ##
## Substrings are separated by a substring containing only `seps`. Note ## Substrings are separated by a substring containing only `seps`. Note
@ -367,15 +367,20 @@ iterator split*(s: string, seps: set[char] = Whitespace): string =
## "08.398990" ## "08.398990"
## ##
var last = 0 var last = 0
var splits = maxsplit
assert(not ('\0' in seps)) assert(not ('\0' in seps))
while last < len(s): while last < len(s):
while s[last] in seps: inc(last) while s[last] in seps: inc(last)
var first = last var first = last
while last < len(s) and s[last] notin seps: inc(last) # BUGFIX! while last < len(s) and s[last] notin seps: inc(last) # BUGFIX!
if first <= last-1: if first <= last-1:
if splits == 0:
yield substr(s, first, len(s)-1)
break
yield substr(s, first, last-1) yield substr(s, first, last-1)
dec(splits)
iterator split*(s: string, sep: char): string = iterator split*(s: string, sep: char, maxsplit: int = -1): string =
## Splits the string `s` into substrings using a single separator. ## Splits the string `s` into substrings using a single separator.
## ##
## Substrings are separated by the character `sep`. ## Substrings are separated by the character `sep`.
@ -402,26 +407,36 @@ iterator split*(s: string, sep: char): string =
## "" ## ""
## ##
var last = 0 var last = 0
var splits = maxsplit
assert('\0' != sep) assert('\0' != sep)
if len(s) > 0: if len(s) > 0:
# `<=` is correct here for the edge cases! # `<=` is correct here for the edge cases!
while last <= len(s): while last <= len(s):
var first = last var first = last
while last < len(s) and s[last] != sep: inc(last) while last < len(s) and s[last] != sep: inc(last)
if splits == 0:
yield substr(s, first, len(s)-1)
break
yield substr(s, first, last-1) yield substr(s, first, last-1)
dec(splits)
inc(last) inc(last)
iterator split*(s: string, sep: string): string = iterator split*(s: string, sep: string, maxsplit: int = -1): string =
## Splits the string `s` into substrings using a string separator. ## Splits the string `s` into substrings using a string separator.
## ##
## Substrings are separated by the string `sep`. ## Substrings are separated by the string `sep`.
var last = 0 var last = 0
var splits = maxsplit
if len(s) > 0: if len(s) > 0:
while last <= len(s): while last <= len(s):
var first = last var first = last
while last < len(s) and s.substr(last, last + <sep.len) != sep: while last < len(s) and s.substr(last, last + <sep.len) != sep:
inc(last) inc(last)
if splits == 0:
yield substr(s, first, len(s)-1)
break
yield substr(s, first, last-1) yield substr(s, first, last-1)
dec(splits)
inc(last, sep.len) inc(last, sep.len)
iterator splitLines*(s: string): string = iterator splitLines*(s: string): string =
@ -491,25 +506,25 @@ proc countLines*(s: string): int {.noSideEffect,
else: discard else: discard
inc i inc i
proc split*(s: string, seps: set[char] = Whitespace): seq[string] {. proc split*(s: string, seps: set[char] = Whitespace, maxsplit: int = -1): seq[string] {.
noSideEffect, rtl, extern: "nsuSplitCharSet".} = noSideEffect, rtl, extern: "nsuSplitCharSet".} =
## The same as the `split iterator <#split.i,string,set[char]>`_, but is a ## The same as the `split iterator <#split.i,string,set[char]>`_, but is a
## proc that returns a sequence of substrings. ## proc that returns a sequence of substrings.
accumulateResult(split(s, seps)) accumulateResult(split(s, seps, maxsplit))
proc split*(s: string, sep: char): seq[string] {.noSideEffect, proc split*(s: string, sep: char, maxsplit: int = -1): seq[string] {.noSideEffect,
rtl, extern: "nsuSplitChar".} = rtl, extern: "nsuSplitChar".} =
## The same as the `split iterator <#split.i,string,char>`_, but is a proc ## The same as the `split iterator <#split.i,string,char>`_, but is a proc
## that returns a sequence of substrings. ## that returns a sequence of substrings.
accumulateResult(split(s, sep)) accumulateResult(split(s, sep, maxsplit))
proc split*(s: string, sep: string): seq[string] {.noSideEffect, proc split*(s: string, sep: string, maxsplit: int = -1): seq[string] {.noSideEffect,
rtl, extern: "nsuSplitString".} = rtl, extern: "nsuSplitString".} =
## Splits the string `s` into substrings using a string separator. ## Splits the string `s` into substrings using a string separator.
## ##
## Substrings are separated by the string `sep`. This is a wrapper around the ## Substrings are separated by the string `sep`. This is a wrapper around the
## `split iterator <#split.i,string,string>`_. ## `split iterator <#split.i,string,string>`_.
accumulateResult(split(s, sep)) accumulateResult(split(s, sep, maxsplit))
proc toHex*(x: BiggestInt, len: Positive): string {.noSideEffect, proc toHex*(x: BiggestInt, len: Positive): string {.noSideEffect,
rtl, extern: "nsuToHex".} = rtl, extern: "nsuToHex".} =