|
0
|
1 .\" Automatically generated by Pod::Man 2.25 (Pod::Simple 3.22)
|
|
|
2 .\"
|
|
|
3 .\" Standard preamble:
|
|
|
4 .\" ========================================================================
|
|
|
5 .de Sp \" Vertical space (when we can't use .PP)
|
|
|
6 .if t .sp .5v
|
|
|
7 .if n .sp
|
|
|
8 ..
|
|
|
9 .de Vb \" Begin verbatim text
|
|
|
10 .ft CW
|
|
|
11 .nf
|
|
|
12 .ne \\$1
|
|
|
13 ..
|
|
|
14 .de Ve \" End verbatim text
|
|
|
15 .ft R
|
|
|
16 .fi
|
|
|
17 ..
|
|
|
18 .\" Set up some character translations and predefined strings. \*(-- will
|
|
|
19 .\" give an unbreakable dash, \*(PI will give pi, \*(L" will give a left
|
|
|
20 .\" double quote, and \*(R" will give a right double quote. \*(C+ will
|
|
|
21 .\" give a nicer C++. Capital omega is used to do unbreakable dashes and
|
|
|
22 .\" therefore won't be available. \*(C` and \*(C' expand to `' in nroff,
|
|
|
23 .\" nothing in troff, for use with C<>.
|
|
|
24 .tr \(*W-
|
|
|
25 .ds C+ C\v'-.1v'\h'-1p'\s-2+\h'-1p'+\s0\v'.1v'\h'-1p'
|
|
|
26 .ie n \{\
|
|
|
27 . ds -- \(*W-
|
|
|
28 . ds PI pi
|
|
|
29 . if (\n(.H=4u)&(1m=24u) .ds -- \(*W\h'-12u'\(*W\h'-12u'-\" diablo 10 pitch
|
|
|
30 . if (\n(.H=4u)&(1m=20u) .ds -- \(*W\h'-12u'\(*W\h'-8u'-\" diablo 12 pitch
|
|
|
31 . ds L" ""
|
|
|
32 . ds R" ""
|
|
|
33 . ds C` ""
|
|
|
34 . ds C' ""
|
|
|
35 'br\}
|
|
|
36 .el\{\
|
|
|
37 . ds -- \|\(em\|
|
|
|
38 . ds PI \(*p
|
|
|
39 . ds L" ``
|
|
|
40 . ds R" ''
|
|
|
41 'br\}
|
|
|
42 .\"
|
|
|
43 .\" Escape single quotes in literal strings from groff's Unicode transform.
|
|
|
44 .ie \n(.g .ds Aq \(aq
|
|
|
45 .el .ds Aq '
|
|
|
46 .\"
|
|
|
47 .\" If the F register is turned on, we'll generate index entries on stderr for
|
|
|
48 .\" titles (.TH), headers (.SH), subsections (.SS), items (.Ip), and index
|
|
|
49 .\" entries marked with X<> in POD. Of course, you'll have to process the
|
|
|
50 .\" output yourself in some meaningful fashion.
|
|
|
51 .ie \nF \{\
|
|
|
52 . de IX
|
|
|
53 . tm Index:\\$1\t\\n%\t"\\$2"
|
|
|
54 ..
|
|
|
55 . nr % 0
|
|
|
56 . rr F
|
|
|
57 .\}
|
|
|
58 .el \{\
|
|
|
59 . de IX
|
|
|
60 ..
|
|
|
61 .\}
|
|
|
62 .\"
|
|
|
63 .\" Accent mark definitions (@(#)ms.acc 1.5 88/02/08 SMI; from UCB 4.2).
|
|
|
64 .\" Fear. Run. Save yourself. No user-serviceable parts.
|
|
|
65 . \" fudge factors for nroff and troff
|
|
|
66 .if n \{\
|
|
|
67 . ds #H 0
|
|
|
68 . ds #V .8m
|
|
|
69 . ds #F .3m
|
|
|
70 . ds #[ \f1
|
|
|
71 . ds #] \fP
|
|
|
72 .\}
|
|
|
73 .if t \{\
|
|
|
74 . ds #H ((1u-(\\\\n(.fu%2u))*.13m)
|
|
|
75 . ds #V .6m
|
|
|
76 . ds #F 0
|
|
|
77 . ds #[ \&
|
|
|
78 . ds #] \&
|
|
|
79 .\}
|
|
|
80 . \" simple accents for nroff and troff
|
|
|
81 .if n \{\
|
|
|
82 . ds ' \&
|
|
|
83 . ds ` \&
|
|
|
84 . ds ^ \&
|
|
|
85 . ds , \&
|
|
|
86 . ds ~ ~
|
|
|
87 . ds /
|
|
|
88 .\}
|
|
|
89 .if t \{\
|
|
|
90 . ds ' \\k:\h'-(\\n(.wu*8/10-\*(#H)'\'\h"|\\n:u"
|
|
|
91 . ds ` \\k:\h'-(\\n(.wu*8/10-\*(#H)'\`\h'|\\n:u'
|
|
|
92 . ds ^ \\k:\h'-(\\n(.wu*10/11-\*(#H)'^\h'|\\n:u'
|
|
|
93 . ds , \\k:\h'-(\\n(.wu*8/10)',\h'|\\n:u'
|
|
|
94 . ds ~ \\k:\h'-(\\n(.wu-\*(#H-.1m)'~\h'|\\n:u'
|
|
|
95 . ds / \\k:\h'-(\\n(.wu*8/10-\*(#H)'\z\(sl\h'|\\n:u'
|
|
|
96 .\}
|
|
|
97 . \" troff and (daisy-wheel) nroff accents
|
|
|
98 .ds : \\k:\h'-(\\n(.wu*8/10-\*(#H+.1m+\*(#F)'\v'-\*(#V'\z.\h'.2m+\*(#F'.\h'|\\n:u'\v'\*(#V'
|
|
|
99 .ds 8 \h'\*(#H'\(*b\h'-\*(#H'
|
|
|
100 .ds o \\k:\h'-(\\n(.wu+\w'\(de'u-\*(#H)/2u'\v'-.3n'\*(#[\z\(de\v'.3n'\h'|\\n:u'\*(#]
|
|
|
101 .ds d- \h'\*(#H'\(pd\h'-\w'~'u'\v'-.25m'\f2\(hy\fP\v'.25m'\h'-\*(#H'
|
|
|
102 .ds D- D\\k:\h'-\w'D'u'\v'-.11m'\z\(hy\v'.11m'\h'|\\n:u'
|
|
|
103 .ds th \*(#[\v'.3m'\s+1I\s-1\v'-.3m'\h'-(\w'I'u*2/3)'\s-1o\s+1\*(#]
|
|
|
104 .ds Th \*(#[\s+2I\s-2\h'-\w'I'u*3/5'\v'-.3m'o\v'.3m'\*(#]
|
|
|
105 .ds ae a\h'-(\w'a'u*4/10)'e
|
|
|
106 .ds Ae A\h'-(\w'A'u*4/10)'E
|
|
|
107 . \" corrections for vroff
|
|
|
108 .if v .ds ~ \\k:\h'-(\\n(.wu*9/10-\*(#H)'\s-2\u~\d\s+2\h'|\\n:u'
|
|
|
109 .if v .ds ^ \\k:\h'-(\\n(.wu*10/11-\*(#H)'\v'-.4m'^\v'.4m'\h'|\\n:u'
|
|
|
110 . \" for low resolution devices (crt and lpr)
|
|
|
111 .if \n(.H>23 .if \n(.V>19 \
|
|
|
112 \{\
|
|
|
113 . ds : e
|
|
|
114 . ds 8 ss
|
|
|
115 . ds o a
|
|
|
116 . ds d- d\h'-1'\(ga
|
|
|
117 . ds D- D\h'-1'\(hy
|
|
|
118 . ds th \o'bp'
|
|
|
119 . ds Th \o'LP'
|
|
|
120 . ds ae ae
|
|
|
121 . ds Ae AE
|
|
|
122 .\}
|
|
|
123 .rm #[ #] #H #V #F C
|
|
|
124 .\" ========================================================================
|
|
|
125 .\"
|
|
|
126 .IX Title "TEXTUTIL 1"
|
|
|
127 .TH TEXTUTIL 1 "2015-03-29" "perl v5.14.2" "MayaChemTools"
|
|
|
128 .\" For nroff, turn off justification. Always turn off hyphenation; it makes
|
|
|
129 .\" way too many mistakes in technical documents.
|
|
|
130 .if n .ad l
|
|
|
131 .nh
|
|
|
132 .SH "NAME"
|
|
|
133 TextUtil
|
|
|
134 .SH "SYNOPSIS"
|
|
|
135 .IX Header "SYNOPSIS"
|
|
|
136 use TextUtil;
|
|
|
137 .PP
|
|
|
138 use TextUtil qw(:all);
|
|
|
139 .SH "DESCRIPTION"
|
|
|
140 .IX Header "DESCRIPTION"
|
|
|
141 \&\fBTextUtil\fR module provides the following functions:
|
|
|
142 .PP
|
|
|
143 AddNumberSuffix, ContainsWhiteSpaces, GetTextFileDataByNonUniqueKey,
|
|
|
144 GetTextFileDataByUniqueKey, GetTextLine, HashCode, IsEmpty, IsFloat, IsInteger,
|
|
|
145 IsNotEmpty, IsNumberPowerOfNumber, IsNumerical, IsPositiveInteger, JoinWords,
|
|
|
146 QuoteAWord, RemoveLeadingAndTrailingWhiteSpaces, RemoveLeadingWhiteSpaces,
|
|
|
147 RemoveTrailingWhiteSpaces, SplitWords, WrapText
|
|
|
148 .SH "FUNCTIONS"
|
|
|
149 .IX Header "FUNCTIONS"
|
|
|
150 .IP "\fBAddNumberSuffix\fR" 4
|
|
|
151 .IX Item "AddNumberSuffix"
|
|
|
152 .Vb 1
|
|
|
153 \& $NumberWithSuffix = AddNumberSuffix($IntegerValue);
|
|
|
154 .Ve
|
|
|
155 .Sp
|
|
|
156 Returns number with appropriate suffix: 0, 1st, 2nd, 3rd, 4th, and so on.
|
|
|
157 .IP "\fBContainsWhiteSpaces\fR" 4
|
|
|
158 .IX Item "ContainsWhiteSpaces"
|
|
|
159 .Vb 1
|
|
|
160 \& $Status = ContainsWhiteSpaces($TheString);
|
|
|
161 .Ve
|
|
|
162 .Sp
|
|
|
163 Returns 1 or 0 based on whether the string contains any white spaces.
|
|
|
164 .IP "\fBGetTextLine\fR" 4
|
|
|
165 .IX Item "GetTextLine"
|
|
|
166 .Vb 1
|
|
|
167 \& $Line = GetTextLine(\e*TEXTFILE);
|
|
|
168 .Ve
|
|
|
169 .Sp
|
|
|
170 Reads next line from an already opened text file, takes out any carriage return,
|
|
|
171 and returns it as a string. \s-1NULL\s0 is returned for \s-1EOF\s0.
|
|
|
172 .IP "\fBGetTextFileDataByNonUniqueKey\fR" 4
|
|
|
173 .IX Item "GetTextFileDataByNonUniqueKey"
|
|
|
174 .Vb 2
|
|
|
175 \& GetTextFileDataByNonUniqueKey($TextDataFile, $TextDataMapRef,
|
|
|
176 \& $DataKeyColNum, $InDelim);
|
|
|
177 .Ve
|
|
|
178 .Sp
|
|
|
179 Load data from a text file into the specified hash reference using a specific
|
|
|
180 column for non-unique data key values.
|
|
|
181 .Sp
|
|
|
182 The lines starting with # are treated as comments and ignored. First line
|
|
|
183 not starting with # must contain column labels and the number of columns in
|
|
|
184 all other data rows must match the number of column labels.
|
|
|
185 .Sp
|
|
|
186 The first column is assumed to contain data key value by default; all other columns
|
|
|
187 contain data as indicated in their column labels.
|
|
|
188 .Sp
|
|
|
189 In order to avoid dependence of data access on the specified column labels, the
|
|
|
190 column data is loaded into hash with Column<Num> hash keys, where column number
|
|
|
191 start from 1. The data key column is not available as Colnum<Num> hash key;
|
|
|
192 .Sp
|
|
|
193 The format of the data structure loaded into a specified hash reference is:
|
|
|
194 .Sp
|
|
|
195 .Vb 7
|
|
|
196 \& @{$TextDataMapRef\->{DataKeys}} \- Array of unique data keys
|
|
|
197 \& @{$TextDataMapRef\->{ColLabels}} \- Array of column labels
|
|
|
198 \& @{$TextDataMapRef\->{DataColIDs}} \- Array of data column IDs
|
|
|
199 \& $TextDataMapRef\->{NumOfCols} \- Number of columns
|
|
|
200 \& %{$TextDataMapRef\->{DataKey}} \- Hash keys pair: <DataKey, DataKey>
|
|
|
201 \& @{$TextDataMapRef\->{DataCol<Num>}} \- Hash keys pair with data as an array:
|
|
|
202 \& <DataCol<Num>, DataKey>
|
|
|
203 .Ve
|
|
|
204 .IP "\fBGetTextFileDataByUniqueKey\fR" 4
|
|
|
205 .IX Item "GetTextFileDataByUniqueKey"
|
|
|
206 .Vb 2
|
|
|
207 \& GetTextFileDataByUniqueKey($TextDataFile, $TextDataMapRef, $DataKeyColNum,
|
|
|
208 \& $InDelim);
|
|
|
209 .Ve
|
|
|
210 .Sp
|
|
|
211 Load data from a text file into the specified hash reference using a a specific
|
|
|
212 column for unique data key values.
|
|
|
213 .Sp
|
|
|
214 The lines starting with # are treated as comments and ignored. First line
|
|
|
215 not starting with # must contain column labels and the number of columns in
|
|
|
216 all other data rows must match the number of column labels.
|
|
|
217 .Sp
|
|
|
218 The first column is assumed to contain data key value by default; all other columns
|
|
|
219 contain data as indicated in their column labels.
|
|
|
220 .Sp
|
|
|
221 In order to avoid dependence of data access on the specified column labels, the
|
|
|
222 column data is loaded into hash with Column<Num> hash keys, where column number
|
|
|
223 start from 1. The data key column is not available as Colnum<Num> hash key;
|
|
|
224 .Sp
|
|
|
225 The format of the data structure loaded into a specified hash reference is:
|
|
|
226 .Sp
|
|
|
227 .Vb 6
|
|
|
228 \& @{$TextDataMapRef\->{DataKeys}} \- Array of unique data keys
|
|
|
229 \& @{$TextDataMapRef\->{ColLabels}} \- Array of column labels
|
|
|
230 \& @{$TextDataMapRef\->{DataColIDs}} \- Array of data column IDs
|
|
|
231 \& $TextDataMapRef\->{NumOfCols} \- Number of columns
|
|
|
232 \& %{$TextDataMapRef\->{DataKey}} \- Hash keys pair: <DataKey, DataKey>
|
|
|
233 \& %{$TextDataMapRef\->{DataCol<Num>}} \- Hash keys pair: <DataCol<Num>, DataKey>
|
|
|
234 .Ve
|
|
|
235 .IP "\fBHashCode\fR" 4
|
|
|
236 .IX Item "HashCode"
|
|
|
237 .Vb 1
|
|
|
238 \& $HashCode = HashCode($TheString);
|
|
|
239 .Ve
|
|
|
240 .Sp
|
|
|
241 Returns a 32 bit integer hash code using One-at-a-time algorithm By Bob Jenkins [Ref 38].
|
|
|
242 It's also implemented in Perl for internal hash keys in hv.h include file.
|
|
|
243 .IP "\fBIsEmpty\fR" 4
|
|
|
244 .IX Item "IsEmpty"
|
|
|
245 .Vb 1
|
|
|
246 \& $Status = IsEmpty($TheString);
|
|
|
247 .Ve
|
|
|
248 .Sp
|
|
|
249 Returns 1 or 0 based on whether the string is empty.
|
|
|
250 .IP "\fBIsInteger\fR" 4
|
|
|
251 .IX Item "IsInteger"
|
|
|
252 .Vb 1
|
|
|
253 \& $Status = IsInteger($TheString);
|
|
|
254 .Ve
|
|
|
255 .Sp
|
|
|
256 Returns 1 or 0 based on whether the string is a positive integer.
|
|
|
257 .IP "\fBIsPositiveInteger\fR" 4
|
|
|
258 .IX Item "IsPositiveInteger"
|
|
|
259 .Vb 1
|
|
|
260 \& $Status = IsPositiveInteger($TheString);
|
|
|
261 .Ve
|
|
|
262 .Sp
|
|
|
263 Returns 1 or 0 based on whether the string is an integer.
|
|
|
264 .IP "\fBIsFloat\fR" 4
|
|
|
265 .IX Item "IsFloat"
|
|
|
266 .Vb 1
|
|
|
267 \& $Status = IsFloat($TheString);
|
|
|
268 .Ve
|
|
|
269 .Sp
|
|
|
270 Returns 1 or 0 based on whether the string is a float.
|
|
|
271 .IP "\fBIsNotEmpty\fR" 4
|
|
|
272 .IX Item "IsNotEmpty"
|
|
|
273 .Vb 1
|
|
|
274 \& $Status = IsNotEmpty($TheString);
|
|
|
275 .Ve
|
|
|
276 .Sp
|
|
|
277 Returns 0 or 1 based on whether the string is empty.
|
|
|
278 .IP "\fBIsNumerical\fR" 4
|
|
|
279 .IX Item "IsNumerical"
|
|
|
280 .Vb 1
|
|
|
281 \& $Status = IsNumerical($TheString);
|
|
|
282 .Ve
|
|
|
283 .Sp
|
|
|
284 Returns 1 or 0 based on whether the string is a number.
|
|
|
285 .IP "\fBIsNumberPowerOfNumber\fR" 4
|
|
|
286 .IX Item "IsNumberPowerOfNumber"
|
|
|
287 .Vb 1
|
|
|
288 \& $Status = IsNumberPowerOfNumber($FirstNum, $SecondNum);
|
|
|
289 .Ve
|
|
|
290 .Sp
|
|
|
291 Returns 1 or 0 based on whether the first number is a power of second number.
|
|
|
292 .IP "\fBJoinWords\fR" 4
|
|
|
293 .IX Item "JoinWords"
|
|
|
294 .Vb 1
|
|
|
295 \& $JoinedWords = JoinWords($Words, $Delim, $Quote);
|
|
|
296 .Ve
|
|
|
297 .Sp
|
|
|
298 Joins different words using delimiter and quote parameters, and returns it
|
|
|
299 as a string.
|
|
|
300 .IP "\fBQuoteAWord\fR" 4
|
|
|
301 .IX Item "QuoteAWord"
|
|
|
302 .Vb 1
|
|
|
303 \& $QuotedWord = QuoteAWord($Word, $Quote);
|
|
|
304 .Ve
|
|
|
305 .Sp
|
|
|
306 Returns a quoted string based on \fIQuote\fR value.
|
|
|
307 .IP "\fBRemoveLeadingWhiteSpaces\fR" 4
|
|
|
308 .IX Item "RemoveLeadingWhiteSpaces"
|
|
|
309 .Vb 1
|
|
|
310 \& $OutString = RemoveLeadingWhiteSpaces($InString);
|
|
|
311 .Ve
|
|
|
312 .Sp
|
|
|
313 Returns a string without any leading and traling white spaces.
|
|
|
314 .IP "\fBRemoveTrailingWhiteSpaces\fR" 4
|
|
|
315 .IX Item "RemoveTrailingWhiteSpaces"
|
|
|
316 .Vb 1
|
|
|
317 \& $OutString = RemoveTrailingWhiteSpaces($InString);
|
|
|
318 .Ve
|
|
|
319 .Sp
|
|
|
320 Returns a string without any trailing white spaces.
|
|
|
321 .IP "\fBRemoveLeadingAndTrailingWhiteSpaces\fR" 4
|
|
|
322 .IX Item "RemoveLeadingAndTrailingWhiteSpaces"
|
|
|
323 .Vb 1
|
|
|
324 \& $OutString = RemoveLeadingAndTrailingWhiteSpaces($InString);
|
|
|
325 .Ve
|
|
|
326 .Sp
|
|
|
327 Returns a string without any leading and traling white spaces.
|
|
|
328 .IP "\fBSplitWords\fR" 4
|
|
|
329 .IX Item "SplitWords"
|
|
|
330 .Vb 1
|
|
|
331 \& @Words = SplitWords($Line, $Delimiter);
|
|
|
332 .Ve
|
|
|
333 .Sp
|
|
|
334 Returns an array \fIWords\fR ontaining unquoted words generated after spliting
|
|
|
335 string value \fILine\fR containing quoted or unquoted words.
|
|
|
336 .Sp
|
|
|
337 This function is used to split strings generated by JoinWords as replacement
|
|
|
338 for Perl's core module funtion \fIText::ParseWords::quotewords()\fR which dumps core
|
|
|
339 on very long strings.
|
|
|
340 .IP "\fBWrapText\fR" 4
|
|
|
341 .IX Item "WrapText"
|
|
|
342 .Vb 1
|
|
|
343 \& $OutString = WrapText($InString, [$WrapLength, $WrapDelimiter]);
|
|
|
344 .Ve
|
|
|
345 .Sp
|
|
|
346 Returns a wrapped string. By default, \fIWrapLenght\fR is \fI40\fR and \fIWrapDelimiter\fR
|
|
|
347 is Unix new line character.
|
|
|
348 .SH "AUTHOR"
|
|
|
349 .IX Header "AUTHOR"
|
|
|
350 Manish Sud <msud@san.rr.com>
|
|
|
351 .SH "SEE ALSO"
|
|
|
352 .IX Header "SEE ALSO"
|
|
|
353 FileUtil.pm
|
|
|
354 .SH "COPYRIGHT"
|
|
|
355 .IX Header "COPYRIGHT"
|
|
|
356 Copyright (C) 2015 Manish Sud. All rights reserved.
|
|
|
357 .PP
|
|
|
358 This file is part of MayaChemTools.
|
|
|
359 .PP
|
|
|
360 MayaChemTools is free software; you can redistribute it and/or modify it under
|
|
|
361 the terms of the \s-1GNU\s0 Lesser General Public License as published by the Free
|
|
|
362 Software Foundation; either version 3 of the License, or (at your option)
|
|
|
363 any later version.
|
