Total Complexity | 53 |
Complexity/F | 10.6 |
Lines of Code | 322 |
Function Count | 5 |
Duplicated Lines | 0 |
Ratio | 0 % |
Changes | 2 | ||
Bugs | 0 | Features | 1 |
Complex classes like src/ub.files.csv.js often do a lot of different things. To break such a class down, we need to identify a cohesive component within that class. A common approach to find such a component is to look for fields/methods that share the same prefixes, or suffixes.
Once you have determined the fields that belong together, you can apply the Extract Class refactoring. If the component makes sense as a sub-class, Extract Subclass is also a candidate, and is often faster.
1 | /** global: UB */ |
||
6 | var fs = require('fs'); |
||
7 | var pathUtil = require('path'); |
||
8 | |||
9 | var arrayFuncs = { |
||
10 | |||
11 | saveToCSV: function(filePath, headers = null, trimValues = true, columnar = false, fixedSep = ",") { |
||
12 | var data = this; |
||
13 | |||
14 | // write CSV to string |
||
15 | var str = data.encodeCSV(headers, trimValues, columnar, fixedSep); |
||
16 | |||
17 | // save data as string via filestream |
||
18 | str.saveToText(filePath); |
||
19 | }, |
||
20 | |||
21 | /** Fast and simple CSV generator. |
||
22 | Supports multi-line values and values with double quotes. |
||
23 | Automatic/smart escaping like Excel-generated CSVs. */ |
||
24 | encodeCSV: function(headers, trimValues, columnar, seperator = ",") { |
||
25 | var linesData = this; |
||
26 | |||
27 | if (columnar) { |
||
28 | linesData = linesData.transpose(); |
||
29 | } |
||
30 | |||
31 | var sb = []; |
||
32 | |||
33 | // per line |
||
34 | for (var l = (headers != null ? -1 : 0), ll = linesData.length - 1; l <= ll; l++) { |
||
1 ignored issue
–
show
|
|||
35 | |||
36 | // fetch header / line data words |
||
37 | var words = l == -1 ? headers : linesData[l]; |
||
38 | |||
39 | // per word |
||
40 | for (var v = 0, vl = words.length - 1; v <= vl; v++) { |
||
41 | |||
42 | // if value given |
||
43 | if (words[v] != null) { |
||
1 ignored issue
–
show
|
|||
44 | |||
45 | // convert value to text |
||
46 | var word = words[v].toString(); |
||
47 | if (trimValues) { |
||
48 | word = word.trim(); |
||
49 | } |
||
50 | |||
51 | // add word |
||
52 | if (word.indexOf('"') > -1) { |
||
53 | |||
54 | // escape quotes, and enclose in quotes if word has a quote |
||
55 | sb.push('"'); |
||
56 | sb.push(word.split("\"").join("\"\"")); |
||
57 | sb.push('"'); |
||
58 | |||
59 | } else if (word.indexOf(',') > -1) { |
||
60 | |||
61 | // enclose in quotes if word has comma |
||
62 | sb.push('"'); |
||
63 | sb.push(word); |
||
64 | sb.push('"'); |
||
65 | |||
66 | } else { |
||
67 | |||
68 | // add straightaway otherwise |
||
69 | sb.push(word); |
||
70 | } |
||
71 | } |
||
72 | |||
73 | // add seperator |
||
74 | if (v < vl) { |
||
75 | sb.push(seperator); |
||
76 | } |
||
77 | } |
||
78 | |||
79 | // add newline |
||
80 | if (l < ll) { |
||
81 | sb.push("\r\n"); |
||
82 | } |
||
83 | } |
||
84 | |||
85 | return sb.join(""); |
||
86 | }, |
||
87 | |||
88 | none:null, |
||
89 | } |
||
90 | |||
91 | // register funcs |
||
92 | UB.registerFuncs(Array.prototype, arrayFuncs); |
||
93 | |||
94 | |||
95 | |||
96 | var stringFuncs = { |
||
97 | |||
98 | /** |
||
99 | * Loads the given CSV file, decoding the cell data and returning it as an array. |
||
100 | * Extremely robust and fast CSV parser. Only parser that works with all bizarre but valid test files. |
||
101 | * |
||
102 | * 3 modes are available: |
||
103 | * if `headers` is null - All cells are returned as 2D array. (default) |
||
104 | * if `headers` is given and 0 length - The first row is stored in `headers`, remaining cells and returned as 2D array. |
||
105 | * if `headers` is given and >0 length - All rows are returned as objects, with the given headers treated as the prop names for the objects. |
||
106 | */ |
||
107 | loadCSV: function(encoding = "utf8", headers = null, trimValues = true, columnar = false, seperator = "auto") { |
||
108 | |||
109 | // load text file |
||
110 | var file = this.toString(); |
||
111 | var text = file.loadText(encoding); |
||
112 | if (text == null) { |
||
1 ignored issue
–
show
|
|||
113 | return null; |
||
114 | } |
||
115 | |||
116 | // parse CSV string into Array |
||
117 | return text.decodeCSV(headers, trimValues, columnar, seperator); |
||
118 | }, |
||
119 | |||
120 | /** Decodes the given CSV file string and returns the cell data as an array. |
||
121 | * Extremely robust and fast CSV parser. Only parser that works with all bizarre but valid test files. |
||
122 | * |
||
123 | * 3 modes are available: |
||
124 | * if `headers` is null - All cells are returned as 2D array. (default) |
||
125 | * if `headers` is given and 0 length - The first row is stored in `headers`, remaining cells and returned as 2D array. |
||
126 | * if `headers` is given and >0 length - All rows are returned as objects, with the given headers treated as the prop names for the objects. |
||
127 | */ |
||
128 | decodeCSV: function (headers, trimValues, columnar = false, seperator = "auto") { |
||
129 | var csvString = this.toString(); |
||
130 | |||
131 | // cut String into lines |
||
132 | var lines = csvString.trim().splitLines(); |
||
133 | var sep = seperator == "auto" ? UB.CSV_detectSeperator(csvString, lines.length) : seperator; |
||
134 | |||
135 | // config |
||
136 | var hasHeaders = headers != null; |
||
1 ignored issue
–
show
|
|||
137 | var returnAsObjs = headers.exists(); |
||
138 | |||
139 | // status |
||
140 | var inQuoted = false; |
||
141 | |||
142 | // result |
||
143 | var linesData = []; |
||
144 | var word = []; |
||
145 | var tempHeaders = []; |
||
146 | |||
147 | // per line |
||
148 | for (var l = 0, ll = lines.length; l < ll; l++) { |
||
149 | var line = lines[l]; |
||
150 | var isHeader = (l == 0 && hasHeaders); |
||
1 ignored issue
–
show
|
|||
151 | |||
152 | // if we are in quoted text |
||
153 | if (inQuoted) { |
||
154 | |||
155 | // keep taking chars |
||
156 | |||
157 | }else{ |
||
158 | |||
159 | // save words into headers array / new array |
||
160 | var lineWords = []; |
||
161 | if (isHeader){ |
||
162 | if (returnAsObjs){ |
||
163 | lineWords = tempHeaders; |
||
164 | }else{ |
||
165 | lineWords = headers; |
||
166 | } |
||
167 | } |
||
168 | if (!isHeader) { |
||
169 | linesData.push(lineWords); |
||
170 | } |
||
171 | |||
172 | } |
||
173 | |||
174 | // per char |
||
175 | for (var c = 0, clast = line.length - 1; c <= clast; c++) { |
||
176 | var ch = line.charAt(c); |
||
177 | |||
178 | // if we are in quoted text |
||
179 | if (inQuoted) { |
||
180 | |||
181 | // quotes.. |
||
182 | if (ch == "\"") { |
||
183 | |||
184 | // quote may be escaped |
||
185 | if (line.charAt(c + 1) == "\"") { |
||
186 | c++; |
||
1 ignored issue
–
show
|
|||
187 | word.push("\""); |
||
188 | }else { |
||
189 | |||
190 | // quote means ending quoted text |
||
191 | inQuoted = false; |
||
192 | } |
||
193 | |||
194 | continue; |
||
195 | } |
||
196 | |||
197 | // normal char |
||
198 | word.push(ch); |
||
199 | |||
200 | |||
201 | }else { |
||
202 | |||
203 | // quote means beginning quoted text |
||
204 | if (ch == "\""){ |
||
205 | inQuoted = true; |
||
206 | continue; |
||
207 | } |
||
208 | |||
209 | // comma means end of word |
||
210 | if (ch == sep) { |
||
211 | lineWords.push(trimValues ? word.join("").trim() : word.join("")); |
||
212 | word = []; |
||
213 | continue; |
||
214 | } |
||
215 | |||
216 | // normal char |
||
217 | word.push(ch); |
||
218 | |||
219 | // newline means end of word |
||
220 | if (c == clast) { |
||
221 | lineWords.push(trimValues ? word.join("").trim() : word.join("")); |
||
222 | word = []; |
||
223 | } |
||
224 | |||
225 | } |
||
226 | |||
227 | } |
||
228 | |||
229 | // at end of line take word |
||
230 | if (!inQuoted && word.Length > 0) { |
||
231 | lineWords.push(trimValues ? word.join("").trim() : word.join("")); |
||
232 | word = []; |
||
233 | } |
||
234 | } |
||
235 | |||
236 | // convert array to objs |
||
237 | if (returnAsObjs){ |
||
238 | |||
239 | // go thru all rows |
||
240 | for (var l = 0, ll = linesData.length; l < ll; l++) { |
||
241 | var line = linesData[l]; |
||
242 | var obj = {}; |
||
243 | |||
244 | // convert all cells to obj props |
||
245 | for (var h = 0, hl = headers.length; h < hl; h++) { |
||
246 | var header = headers[h]; |
||
247 | obj[header] = line[h]; |
||
248 | } |
||
249 | linesData[l] = obj; |
||
250 | } |
||
251 | } |
||
252 | |||
253 | // convert 2D array to columnar |
||
254 | if (columnar && !returnAsObjs) { |
||
255 | linesData = linesData.transpose(); |
||
256 | } |
||
257 | |||
258 | return linesData; |
||
259 | }, |
||
260 | |||
261 | none:null, |
||
262 | } |
||
263 | |||
264 | // register funcs |
||
265 | UB.registerFuncs(String.prototype, stringFuncs); |
||
266 | |||
267 | |||
268 | |||
269 | // UTILS |
||
270 | UB.CSV_seperators = [',', ';', ':', '\t']; |
||
271 | |||
272 | UB.CSV_detectSeperator = function(csvString, rowCount) { |
||
273 | var sepCount = UB.newArray(0, UB.CSV_seperators.length); |
||
274 | |||
275 | var character; |
||
276 | |||
277 | var quoted = false; |
||
278 | var firstChar = true; |
||
279 | var foundAny = false; |
||
280 | |||
281 | var c = 0; |
||
282 | var cl = csvString.length - 50; // skip last few chars |
||
283 | while (c < cl) { |
||
284 | character = csvString.charAt(c); |
||
285 | c++; |
||
286 | |||
287 | switch (character) { |
||
288 | case '"': |
||
289 | if (quoted) { |
||
290 | if (csvString.charAt(c + 1) != '"') { // Value is quoted and current character is " and next character is not ". |
||
291 | quoted = false; |
||
292 | } else { |
||
293 | c++; // Value is quoted and current and next characters are "" - read (skip) peeked qoute. |
||
294 | } |
||
295 | } else { |
||
296 | if (firstChar) { // Set value as quoted only if this quote is the first char in the value. |
||
297 | quoted = true; |
||
298 | } |
||
299 | } |
||
300 | break; |
||
301 | case '\r': |
||
302 | case '\n': |
||
303 | if (!quoted) { |
||
304 | firstChar = true; |
||
305 | continue; |
||
306 | } |
||
307 | break; |
||
308 | default: |
||
309 | if (!quoted) { |
||
310 | var index = UB.CSV_seperators.indexOf(character); |
||
311 | if (index != -1) { |
||
312 | sepCount[index]++; |
||
313 | firstChar = true; |
||
314 | foundAny = true; |
||
315 | continue; |
||
316 | } |
||
317 | } |
||
318 | break; |
||
319 | } |
||
320 | |||
321 | if (firstChar) { |
||
322 | firstChar = false; |
||
323 | } |
||
324 | } |
||
325 | |||
326 | return !foundAny ? ',' : UB.CSV_seperators[sepCount.indexOfMax()]; |
||
327 | } |
||
328 | |||
331 |