1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
|
#
#
# Nim's Runtime Library
# (c) Copyright 2018 Nim contributors
#
# See the file "copying.txt", included in this
# distribution, for details about the copyright.
#
## This module contains an algorithm to wordwrap a Unicode string.
import strutils, unicode
proc olen(s: string): int =
var i = 0
result = 0
while i < s.len:
inc result
let L = graphemeLen(s, i)
inc i, L
proc wrapWords*(s: string, maxLineWidth = 80,
splitLongWords = true,
seps: set[char] = Whitespace,
newLine = "\n"): string {.noSideEffect.} =
## Word wraps `s`.
result = newStringOfCap(s.len + s.len shr 6)
var spaceLeft = maxLineWidth
var lastSep = ""
for word, isSep in tokenize(s, seps):
let wlen = olen(word)
if isSep:
lastSep = word
spaceLeft = spaceLeft - wlen
elif wlen > spaceLeft:
if splitLongWords and wlen > maxLineWidth:
var i = 0
while i < word.len:
if spaceLeft <= 0:
spaceLeft = maxLineWidth
result.add newLine
dec spaceLeft
let L = graphemeLen(word, i)
for j in 0 ..< L: result.add word[i+j]
inc i, L
else:
spaceLeft = maxLineWidth - wlen
result.add(newLine)
result.add(word)
else:
spaceLeft = spaceLeft - wlen
result.add(lastSep)
result.add(word)
lastSep.setLen(0)
when isMainModule:
when true:
let
inp = """ this is a long text -- muchlongerthan10chars and here
it goes"""
outp = " this is a\nlong text\n--\nmuchlongerthan10chars\nand here\nit goes"
doAssert wrapWords(inp, 10, false) == outp
let
longInp = """ThisIsOneVeryLongStringWhichWeWillSplitIntoEightSeparatePartsNow"""
longOutp = "ThisIsOn\neVeryLon\ngStringW\nhichWeWi\nllSplitI\nntoEight\nSeparate\nPartsNow"
doAssert wrapWords(longInp, 8, true) == longOutp
# test we don't break Umlauts into invalid bytes:
let fies = "äöüöäöüöäöüöäöüööäöüöäößßßßüöäößßßßßß"
let fiesRes = "ä\nö\nü\nö\nä\nö\nü\nö\nä\nö\nü\nö\nä\nö\nü\nö\nö\nä\nö\nü\nö\nä\nö\nß\nß\nß\nß\nü\nö\nä\nö\nß\nß\nß\nß\nß\nß"
doAssert wrapWords(fies, 1, true) == fiesRes
let longlongword = """abc uitdaeröägfßhydüäpydqfü,träpydqgpmüdträpydföägpydörztdüöäfguiaeowäzjdtrüöäp psnrtuiydrözenrüöäpyfdqazpesnrtulocjtüö
äzydgyqgfqfgprtnwjlcydkqgfüöezmäzydydqüüöäpdtrnvwfhgckdumböäpydfgtdgfhtdrntdrntydfogiayqfguiatrnydrntüöärtniaoeydfgaoeiqfglwcßqfgxvlcwgtfhiaoen
rsüöäapmböäptdrniaoydfglckqfhouenrtsüöäptrniaoeyqfgulocfqclgwxßqflgcwßqfxglcwrniatrnmüböäpmöäbpümöäbpüöämpbaoestnriaesnrtdiaesrtdniaesdrtnaetdr
iaoenvlcyfglwckßqfgvwkßqgfvlwkßqfgvlwckßqvlwkgfUIαοιαοιαχολωχσωχνωκψρχκψρτιεαοσηζϵηζιοεννκεωνιαλωσωκνκψρκγτφγτχκγτεκργτιχνκιωχσιλωσλωχξλξλξωχωχ
ξχλωωχαοεοιαεοαεοιαεοαεοιαοεσναοεκνρκψγκψφϵιηαααοε"""
let longlongwordRes = """
abc uitdaeröägfßhydüäpydqfü,träpydqgpmüdträpydföägpydörztdüöäfguiaeowäzjdtrüöäp
psnrtuiydrözenrüöäpyfdqazpesnrtulocjtüöäzydgyqgfqfgprtnwjlcydkqgfüöezmäzydydqüü
öäpdtrnvwfhgckdumböäpydfgtdgfhtdrntdrntydfogiayqfguiatrnydrntüöärtniaoeydfgaoeiq
fglwcßqfgxvlcwgtfhiaoenrsüöäapmböäptdrniaoydfglckqfhouenrtsüöäptrniaoeyqfgulocf
qclgwxßqflgcwßqfxglcwrniatrnmüböäpmöäbpümöäbpüöämpbaoestnriaesnrtdiaesrtdniaesdr
tnaetdriaoenvlcyfglwckßqfgvwkßqgfvlwkßqfgvlwckßqvlwkgfUIαοιαοιαχολωχσωχνωκψρχκψ
ρτιεαοσηζϵηζιοεννκεωνιαλωσωκνκψρκγτφγτχκγτεκργτιχνκιωχσιλωσλωχξλξλξωχωχ
ξχλωωχαοεοιαεοαεοιαεοαεοιαοεσναοεκνρκψγκψφϵιηαααοε"""
doAssert wrapWords(longlongword) == longlongwordRes
|