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 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357
|
/*
Copyright 2014 Alexander Okoli
Licensed under the Apache License, Version 2.0 (the "License");
you may not use this file except in compliance with the License.
You may obtain a copy of the License at
http://www.apache.org/licenses/LICENSE-2.0
Unless required by applicable law or agreed to in writing, software
distributed under the License is distributed on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
See the License for the specific language governing permissions and
limitations under the License.
*/
/*
Package goutils provides utility functions to manipulate strings in various ways.
The code snippets below show examples of how to use goutils. Some functions return
errors while others do not, so usage would vary as a result.
Example:
package main
import (
"fmt"
"github.com/aokoli/goutils"
)
func main() {
// EXAMPLE 1: A goutils function which returns no errors
fmt.Println (goutils.Initials("John Doe Foo")) // Prints out "JDF"
// EXAMPLE 2: A goutils function which returns an error
rand1, err1 := goutils.Random (-1, 0, 0, true, true)
if err1 != nil {
fmt.Println(err1) // Prints out error message because -1 was entered as the first parameter in goutils.Random(...)
} else {
fmt.Println(rand1)
}
}
*/
package goutils
import (
"bytes"
"strings"
"unicode"
)
// VERSION indicates the current version of goutils
const VERSION = "1.0.0"
/*
Wrap wraps a single line of text, identifying words by ' '.
New lines will be separated by '\n'. Very long words, such as URLs will not be wrapped.
Leading spaces on a new line are stripped. Trailing spaces are not stripped.
Parameters:
str - the string to be word wrapped
wrapLength - the column (a column can fit only one character) to wrap the words at, less than 1 is treated as 1
Returns:
a line with newlines inserted
*/
func Wrap(str string, wrapLength int) string {
return WrapCustom(str, wrapLength, "", false)
}
/*
WrapCustom wraps a single line of text, identifying words by ' '.
Leading spaces on a new line are stripped. Trailing spaces are not stripped.
Parameters:
str - the string to be word wrapped
wrapLength - the column number (a column can fit only one character) to wrap the words at, less than 1 is treated as 1
newLineStr - the string to insert for a new line, "" uses '\n'
wrapLongWords - true if long words (such as URLs) should be wrapped
Returns:
a line with newlines inserted
*/
func WrapCustom(str string, wrapLength int, newLineStr string, wrapLongWords bool) string {
if str == "" {
return ""
}
if newLineStr == "" {
newLineStr = "\n" // TODO Assumes "\n" is seperator. Explore SystemUtils.LINE_SEPARATOR from Apache Commons
}
if wrapLength < 1 {
wrapLength = 1
}
inputLineLength := len(str)
offset := 0
var wrappedLine bytes.Buffer
for inputLineLength-offset > wrapLength {
if rune(str[offset]) == ' ' {
offset++
continue
}
end := wrapLength + offset + 1
spaceToWrapAt := strings.LastIndex(str[offset:end], " ") + offset
if spaceToWrapAt >= offset {
// normal word (not longer than wrapLength)
wrappedLine.WriteString(str[offset:spaceToWrapAt])
wrappedLine.WriteString(newLineStr)
offset = spaceToWrapAt + 1
} else {
// long word or URL
if wrapLongWords {
end := wrapLength + offset
// long words are wrapped one line at a time
wrappedLine.WriteString(str[offset:end])
wrappedLine.WriteString(newLineStr)
offset += wrapLength
} else {
// long words aren't wrapped, just extended beyond limit
end := wrapLength + offset
index := strings.IndexRune(str[end:len(str)], ' ')
if index == -1 {
wrappedLine.WriteString(str[offset:len(str)])
offset = inputLineLength
} else {
spaceToWrapAt = index + end
wrappedLine.WriteString(str[offset:spaceToWrapAt])
wrappedLine.WriteString(newLineStr)
offset = spaceToWrapAt + 1
}
}
}
}
wrappedLine.WriteString(str[offset:len(str)])
return wrappedLine.String()
}
/*
Capitalize capitalizes all the delimiter separated words in a string. Only the first letter of each word is changed.
To convert the rest of each word to lowercase at the same time, use CapitalizeFully(str string, delimiters ...rune).
The delimiters represent a set of characters understood to separate words. The first string character
and the first non-delimiter character after a delimiter will be capitalized. A "" input string returns "".
Capitalization uses the Unicode title case, normally equivalent to upper case.
Parameters:
str - the string to capitalize
delimiters - set of characters to determine capitalization, exclusion of this parameter means whitespace would be delimeter
Returns:
capitalized string
*/
func Capitalize(str string, delimiters ...rune) string {
var delimLen int
if delimiters == nil {
delimLen = -1
} else {
delimLen = len(delimiters)
}
if str == "" || delimLen == 0 {
return str
}
buffer := []rune(str)
capitalizeNext := true
for i := 0; i < len(buffer); i++ {
ch := buffer[i]
if isDelimiter(ch, delimiters...) {
capitalizeNext = true
} else if capitalizeNext {
buffer[i] = unicode.ToTitle(ch)
capitalizeNext = false
}
}
return string(buffer)
}
/*
CapitalizeFully converts all the delimiter separated words in a string into capitalized words, that is each word is made up of a
titlecase character and then a series of lowercase characters. The delimiters represent a set of characters understood
to separate words. The first string character and the first non-delimiter character after a delimiter will be capitalized.
Capitalization uses the Unicode title case, normally equivalent to upper case.
Parameters:
str - the string to capitalize fully
delimiters - set of characters to determine capitalization, exclusion of this parameter means whitespace would be delimeter
Returns:
capitalized string
*/
func CapitalizeFully(str string, delimiters ...rune) string {
var delimLen int
if delimiters == nil {
delimLen = -1
} else {
delimLen = len(delimiters)
}
if str == "" || delimLen == 0 {
return str
}
str = strings.ToLower(str)
return Capitalize(str, delimiters...)
}
/*
Uncapitalize uncapitalizes all the whitespace separated words in a string. Only the first letter of each word is changed.
The delimiters represent a set of characters understood to separate words. The first string character and the first non-delimiter
character after a delimiter will be uncapitalized. Whitespace is defined by unicode.IsSpace(char).
Parameters:
str - the string to uncapitalize fully
delimiters - set of characters to determine capitalization, exclusion of this parameter means whitespace would be delimeter
Returns:
uncapitalized string
*/
func Uncapitalize(str string, delimiters ...rune) string {
var delimLen int
if delimiters == nil {
delimLen = -1
} else {
delimLen = len(delimiters)
}
if str == "" || delimLen == 0 {
return str
}
buffer := []rune(str)
uncapitalizeNext := true // TODO Always makes capitalize/un apply to first char.
for i := 0; i < len(buffer); i++ {
ch := buffer[i]
if isDelimiter(ch, delimiters...) {
uncapitalizeNext = true
} else if uncapitalizeNext {
buffer[i] = unicode.ToLower(ch)
uncapitalizeNext = false
}
}
return string(buffer)
}
/*
SwapCase swaps the case of a string using a word based algorithm.
Conversion algorithm:
Upper case character converts to Lower case
Title case character converts to Lower case
Lower case character after Whitespace or at start converts to Title case
Other Lower case character converts to Upper case
Whitespace is defined by unicode.IsSpace(char).
Parameters:
str - the string to swap case
Returns:
the changed string
*/
func SwapCase(str string) string {
if str == "" {
return str
}
buffer := []rune(str)
whitespace := true
for i := 0; i < len(buffer); i++ {
ch := buffer[i]
if unicode.IsUpper(ch) {
buffer[i] = unicode.ToLower(ch)
whitespace = false
} else if unicode.IsTitle(ch) {
buffer[i] = unicode.ToLower(ch)
whitespace = false
} else if unicode.IsLower(ch) {
if whitespace {
buffer[i] = unicode.ToTitle(ch)
whitespace = false
} else {
buffer[i] = unicode.ToUpper(ch)
}
} else {
whitespace = unicode.IsSpace(ch)
}
}
return string(buffer)
}
/*
Initials extracts the initial letters from each word in the string. The first letter of the string and all first
letters after the defined delimiters are returned as a new string. Their case is not changed. If the delimiters
parameter is excluded, then Whitespace is used. Whitespace is defined by unicode.IsSpacea(char). An empty delimiter array returns an empty string.
Parameters:
str - the string to get initials from
delimiters - set of characters to determine words, exclusion of this parameter means whitespace would be delimeter
Returns:
string of initial letters
*/
func Initials(str string, delimiters ...rune) string {
if str == "" {
return str
}
if delimiters != nil && len(delimiters) == 0 {
return ""
}
strLen := len(str)
var buf bytes.Buffer
lastWasGap := true
for i := 0; i < strLen; i++ {
ch := rune(str[i])
if isDelimiter(ch, delimiters...) {
lastWasGap = true
} else if lastWasGap {
buf.WriteRune(ch)
lastWasGap = false
}
}
return buf.String()
}
// private function (lower case func name)
func isDelimiter(ch rune, delimiters ...rune) bool {
if delimiters == nil {
return unicode.IsSpace(ch)
}
for _, delimiter := range delimiters {
if ch == delimiter {
return true
}
}
return false
}
|