| 1 |
.\" -*- mode: troff; coding: utf-8 -*- |
| 2 |
.\" Automatically generated by Pod::Man 5.0102 (Pod::Simple 3.45) |
| 3 |
.\" |
| 4 |
.\" Standard preamble: |
| 5 |
.\" ======================================================================== |
| 6 |
.de Sp \" Vertical space (when we can't use .PP) |
| 7 |
.if t .sp .5v |
| 8 |
.if n .sp |
| 9 |
.. |
| 10 |
.de Vb \" Begin verbatim text |
| 11 |
.ft CW |
| 12 |
.nf |
| 13 |
.ne \\$1 |
| 14 |
.. |
| 15 |
.de Ve \" End verbatim text |
| 16 |
.ft R |
| 17 |
.fi |
| 18 |
.. |
| 19 |
.\" \*(C` and \*(C' are quotes in nroff, nothing in troff, for use with C<>. |
| 20 |
.ie n \{\ |
| 21 |
. ds C` "" |
| 22 |
. ds C' "" |
| 23 |
'br\} |
| 24 |
.el\{\ |
| 25 |
. ds C` |
| 26 |
. ds C' |
| 27 |
'br\} |
| 28 |
.\" |
| 29 |
.\" Escape single quotes in literal strings from groff's Unicode transform. |
| 30 |
.ie \n(.g .ds Aq \(aq |
| 31 |
.el .ds Aq ' |
| 32 |
.\" |
| 33 |
.\" If the F register is >0, we'll generate index entries on stderr for |
| 34 |
.\" titles (.TH), headers (.SH), subsections (.SS), items (.Ip), and index |
| 35 |
.\" entries marked with X<> in POD. Of course, you'll have to process the |
| 36 |
.\" output yourself in some meaningful fashion. |
| 37 |
.\" |
| 38 |
.\" Avoid warning from groff about undefined register 'F'. |
| 39 |
.de IX |
| 40 |
.. |
| 41 |
.nr rF 0 |
| 42 |
.if \n(.g .if rF .nr rF 1 |
| 43 |
.if (\n(rF:(\n(.g==0)) \{\ |
| 44 |
. if \nF \{\ |
| 45 |
. de IX |
| 46 |
. tm Index:\\$1\t\\n%\t"\\$2" |
| 47 |
.. |
| 48 |
. if !\nF==2 \{\ |
| 49 |
. nr % 0 |
| 50 |
. nr F 2 |
| 51 |
. \} |
| 52 |
. \} |
| 53 |
.\} |
| 54 |
.rr rF |
| 55 |
.\" ======================================================================== |
| 56 |
.\" |
| 57 |
.IX Title "File::GlobMapper 3perl" |
| 58 |
.TH File::GlobMapper 3perl 2025-11-16 "perl v5.40.1" "Perl Programmers Reference Guide" |
| 59 |
.\" For nroff, turn off justification. Always turn off hyphenation; it makes |
| 60 |
.\" way too many mistakes in technical documents. |
| 61 |
.if n .ad l |
| 62 |
.nh |
| 63 |
.SH NAME |
| 64 |
File::GlobMapper \- Extend File Glob to Allow Input and Output Files |
| 65 |
.SH SYNOPSIS |
| 66 |
.IX Header "SYNOPSIS" |
| 67 |
.Vb 1 |
| 68 |
\& use File::GlobMapper qw( globmap ); |
| 69 |
\& |
| 70 |
\& my $aref = globmap $input => $output |
| 71 |
\& or die $File::GlobMapper::Error ; |
| 72 |
\& |
| 73 |
\& my $gm = File::GlobMapper\->new( $input => $output ) |
| 74 |
\& or die $File::GlobMapper::Error ; |
| 75 |
.Ve |
| 76 |
.SH DESCRIPTION |
| 77 |
.IX Header "DESCRIPTION" |
| 78 |
This module needs Perl5.005 or better. |
| 79 |
.PP |
| 80 |
This module takes the existing \f(CW\*(C`File::Glob\*(C'\fR module as a starting point and |
| 81 |
extends it to allow new filenames to be derived from the files matched by |
| 82 |
\&\f(CW\*(C`File::Glob\*(C'\fR. |
| 83 |
.PP |
| 84 |
This can be useful when carrying out batch operations on multiple files that |
| 85 |
have both an input filename and output filename and the output file can be |
| 86 |
derived from the input filename. Examples of operations where this can be |
| 87 |
useful include, file renaming, file copying and file compression. |
| 88 |
.SS "Behind The Scenes" |
| 89 |
.IX Subsection "Behind The Scenes" |
| 90 |
To help explain what \f(CW\*(C`File::GlobMapper\*(C'\fR does, consider what code you |
| 91 |
would write if you wanted to rename all files in the current directory |
| 92 |
that ended in \f(CW\*(C`.tar.gz\*(C'\fR to \f(CW\*(C`.tgz\*(C'\fR. So say these files are in the |
| 93 |
current directory |
| 94 |
.PP |
| 95 |
.Vb 3 |
| 96 |
\& alpha.tar.gz |
| 97 |
\& beta.tar.gz |
| 98 |
\& gamma.tar.gz |
| 99 |
.Ve |
| 100 |
.PP |
| 101 |
and they need renamed to this |
| 102 |
.PP |
| 103 |
.Vb 3 |
| 104 |
\& alpha.tgz |
| 105 |
\& beta.tgz |
| 106 |
\& gamma.tgz |
| 107 |
.Ve |
| 108 |
.PP |
| 109 |
Below is a possible implementation of a script to carry out the rename |
| 110 |
(error cases have been omitted) |
| 111 |
.PP |
| 112 |
.Vb 4 |
| 113 |
\& foreach my $old ( glob "*.tar.gz" ) |
| 114 |
\& { |
| 115 |
\& my $new = $old; |
| 116 |
\& $new =~ s#(.*)\e.tar\e.gz$#$1.tgz# ; |
| 117 |
\& |
| 118 |
\& rename $old => $new |
| 119 |
\& or die "Cannot rename \*(Aq$old\*(Aq to \*(Aq$new\*(Aq: $!\en; |
| 120 |
\& } |
| 121 |
.Ve |
| 122 |
.PP |
| 123 |
Notice that a file glob pattern \f(CW\*(C`*.tar.gz\*(C'\fR was used to match the |
| 124 |
\&\f(CW\*(C`.tar.gz\*(C'\fR files, then a fairly similar regular expression was used in |
| 125 |
the substitute to allow the new filename to be created. |
| 126 |
.PP |
| 127 |
Given that the file glob is just a cut-down regular expression and that it |
| 128 |
has already done a lot of the hard work in pattern matching the filenames, |
| 129 |
wouldn't it be handy to be able to use the patterns in the fileglob to |
| 130 |
drive the new filename? |
| 131 |
.PP |
| 132 |
Well, that's \fIexactly\fR what \f(CW\*(C`File::GlobMapper\*(C'\fR does. |
| 133 |
.PP |
| 134 |
Here is same snippet of code rewritten using \f(CW\*(C`globmap\*(C'\fR |
| 135 |
.PP |
| 136 |
.Vb 6 |
| 137 |
\& for my $pair (globmap \*(Aq<*.tar.gz>\*(Aq => \*(Aq<#1.tgz>\*(Aq ) |
| 138 |
\& { |
| 139 |
\& my ($from, $to) = @$pair; |
| 140 |
\& rename $from => $to |
| 141 |
\& or die "Cannot rename \*(Aq$old\*(Aq to \*(Aq$new\*(Aq: $!\en; |
| 142 |
\& } |
| 143 |
.Ve |
| 144 |
.PP |
| 145 |
So how does it work? |
| 146 |
.PP |
| 147 |
Behind the scenes the \f(CW\*(C`globmap\*(C'\fR function does a combination of a |
| 148 |
file glob to match existing filenames followed by a substitute |
| 149 |
to create the new filenames. |
| 150 |
.PP |
| 151 |
Notice how both parameters to \f(CW\*(C`globmap\*(C'\fR are strings that are delimited by <>. |
| 152 |
This is done to make them look more like file globs \- it is just syntactic |
| 153 |
sugar, but it can be handy when you want the strings to be visually |
| 154 |
distinctive. The enclosing <> are optional, so you don't have to use them \- in |
| 155 |
fact the first thing globmap will do is remove these delimiters if they are |
| 156 |
present. |
| 157 |
.PP |
| 158 |
The first parameter to \f(CW\*(C`globmap\*(C'\fR, \f(CW\*(C`*.tar.gz\*(C'\fR, is an \fIInput File Glob\fR. |
| 159 |
Once the enclosing "< ... >" is removed, this is passed (more or |
| 160 |
less) unchanged to \f(CW\*(C`File::Glob\*(C'\fR to carry out a file match. |
| 161 |
.PP |
| 162 |
Next the fileglob \f(CW\*(C`*.tar.gz\*(C'\fR is transformed behind the scenes into a |
| 163 |
full Perl regular expression, with the additional step of wrapping each |
| 164 |
transformed wildcard metacharacter sequence in parenthesis. |
| 165 |
.PP |
| 166 |
In this case the input fileglob \f(CW\*(C`*.tar.gz\*(C'\fR will be transformed into |
| 167 |
this Perl regular expression |
| 168 |
.PP |
| 169 |
.Vb 1 |
| 170 |
\& ([^/]*)\e.tar\e.gz |
| 171 |
.Ve |
| 172 |
.PP |
| 173 |
Wrapping with parenthesis allows the wildcard parts of the Input File |
| 174 |
Glob to be referenced by the second parameter to \f(CW\*(C`globmap\*(C'\fR, \f(CW\*(C`#1.tgz\*(C'\fR, |
| 175 |
the \fIOutput File Glob\fR. This parameter operates just like the replacement |
| 176 |
part of a substitute command. The difference is that the \f(CW\*(C`#1\*(C'\fR syntax |
| 177 |
is used to reference sub-patterns matched in the input fileglob, rather |
| 178 |
than the \f(CW$1\fR syntax that is used with perl regular expressions. In |
| 179 |
this case \f(CW\*(C`#1\*(C'\fR is used to refer to the text matched by the \f(CW\*(C`*\*(C'\fR in the |
| 180 |
Input File Glob. This makes it easier to use this module where the |
| 181 |
parameters to \f(CW\*(C`globmap\*(C'\fR are typed at the command line. |
| 182 |
.PP |
| 183 |
The final step involves passing each filename matched by the \f(CW\*(C`*.tar.gz\*(C'\fR |
| 184 |
file glob through the derived Perl regular expression in turn and |
| 185 |
expanding the output fileglob using it. |
| 186 |
.PP |
| 187 |
The end result of all this is a list of pairs of filenames. By default |
| 188 |
that is what is returned by \f(CW\*(C`globmap\*(C'\fR. In this example the data structure |
| 189 |
returned will look like this |
| 190 |
.PP |
| 191 |
.Vb 4 |
| 192 |
\& ( [\*(Aqalpha.tar.gz\*(Aq => \*(Aqalpha.tgz\*(Aq], |
| 193 |
\& [\*(Aqbeta.tar.gz\*(Aq => \*(Aqbeta.tgz\*(Aq ], |
| 194 |
\& [\*(Aqgamma.tar.gz\*(Aq => \*(Aqgamma.tgz\*(Aq] |
| 195 |
\& ) |
| 196 |
.Ve |
| 197 |
.PP |
| 198 |
Each pair is an array reference with two elements \- namely the \fIfrom\fR |
| 199 |
filename, that \f(CW\*(C`File::Glob\*(C'\fR has matched, and a \fIto\fR filename that is |
| 200 |
derived from the \fIfrom\fR filename. |
| 201 |
.SS Limitations |
| 202 |
.IX Subsection "Limitations" |
| 203 |
\&\f(CW\*(C`File::GlobMapper\*(C'\fR has been kept simple deliberately, so it isn't intended to |
| 204 |
solve all filename mapping operations. Under the hood \f(CW\*(C`File::Glob\*(C'\fR (or for |
| 205 |
older versions of Perl, \f(CW\*(C`File::BSDGlob\*(C'\fR) is used to match the files, so you |
| 206 |
will never have the flexibility of full Perl regular expression. |
| 207 |
.SS "Input File Glob" |
| 208 |
.IX Subsection "Input File Glob" |
| 209 |
The syntax for an Input FileGlob is identical to \f(CW\*(C`File::Glob\*(C'\fR, except |
| 210 |
for the following |
| 211 |
.IP 1. 5 |
| 212 |
No nested {} |
| 213 |
.IP 2. 5 |
| 214 |
Whitespace does not delimit fileglobs. |
| 215 |
.IP 3. 5 |
| 216 |
The use of parenthesis can be used to capture parts of the input filename. |
| 217 |
.IP 4. 5 |
| 218 |
If an Input glob matches the same file more than once, only the first |
| 219 |
will be used. |
| 220 |
.PP |
| 221 |
The syntax |
| 222 |
.IP \fB~\fR 5 |
| 223 |
.IX Item "~" |
| 224 |
.PD 0 |
| 225 |
.IP \fB~user\fR 5 |
| 226 |
.IX Item "~user" |
| 227 |
.IP \fB.\fR 5 |
| 228 |
.IX Item "." |
| 229 |
.PD |
| 230 |
Matches a literal '.'. |
| 231 |
Equivalent to the Perl regular expression |
| 232 |
.Sp |
| 233 |
.Vb 1 |
| 234 |
\& \e. |
| 235 |
.Ve |
| 236 |
.IP \fB*\fR 5 |
| 237 |
.IX Item "*" |
| 238 |
Matches zero or more characters, except '/'. Equivalent to the Perl |
| 239 |
regular expression |
| 240 |
.Sp |
| 241 |
.Vb 1 |
| 242 |
\& [^/]* |
| 243 |
.Ve |
| 244 |
.IP \fB?\fR 5 |
| 245 |
.IX Item "?" |
| 246 |
Matches zero or one character, except '/'. Equivalent to the Perl |
| 247 |
regular expression |
| 248 |
.Sp |
| 249 |
.Vb 1 |
| 250 |
\& [^/]? |
| 251 |
.Ve |
| 252 |
.IP \fB\e\fR 5 |
| 253 |
.IX Item "" |
| 254 |
Backslash is used, as usual, to escape the next character. |
| 255 |
.IP \fB[]\fR 5 |
| 256 |
.IX Item "[]" |
| 257 |
Character class. |
| 258 |
.IP \fB{,}\fR 5 |
| 259 |
.IX Item "{,}" |
| 260 |
Alternation |
| 261 |
.IP \fB()\fR 5 |
| 262 |
.IX Item "()" |
| 263 |
Capturing parenthesis that work just like perl |
| 264 |
.PP |
| 265 |
Any other character it taken literally. |
| 266 |
.SS "Output File Glob" |
| 267 |
.IX Subsection "Output File Glob" |
| 268 |
The Output File Glob is a normal string, with 2 glob-like features. |
| 269 |
.PP |
| 270 |
The first is the '*' metacharacter. This will be replaced by the complete |
| 271 |
filename matched by the input file glob. So |
| 272 |
.PP |
| 273 |
.Vb 1 |
| 274 |
\& *.c *.Z |
| 275 |
.Ve |
| 276 |
.PP |
| 277 |
The second is |
| 278 |
.PP |
| 279 |
Output FileGlobs take the |
| 280 |
.IP """*""" 5 |
| 281 |
The "*" character will be replaced with the complete input filename. |
| 282 |
.IP #1 5 |
| 283 |
.IX Item "#1" |
| 284 |
Patterns of the form /#\ed/ will be replaced with the |
| 285 |
.SS "Returned Data" |
| 286 |
.IX Subsection "Returned Data" |
| 287 |
.SH EXAMPLES |
| 288 |
.IX Header "EXAMPLES" |
| 289 |
.SS "A Rename script" |
| 290 |
.IX Subsection "A Rename script" |
| 291 |
Below is a simple "rename" script that uses \f(CW\*(C`globmap\*(C'\fR to determine the |
| 292 |
source and destination filenames. |
| 293 |
.PP |
| 294 |
.Vb 2 |
| 295 |
\& use File::GlobMapper qw(globmap) ; |
| 296 |
\& use File::Copy; |
| 297 |
\& |
| 298 |
\& die "rename: Usage rename \*(Aqfrom\*(Aq \*(Aqto\*(Aq\en" |
| 299 |
\& unless @ARGV == 2 ; |
| 300 |
\& |
| 301 |
\& my $fromGlob = shift @ARGV; |
| 302 |
\& my $toGlob = shift @ARGV; |
| 303 |
\& |
| 304 |
\& my $pairs = globmap($fromGlob, $toGlob) |
| 305 |
\& or die $File::GlobMapper::Error; |
| 306 |
\& |
| 307 |
\& for my $pair (@$pairs) |
| 308 |
\& { |
| 309 |
\& my ($from, $to) = @$pair; |
| 310 |
\& move $from => $to ; |
| 311 |
\& } |
| 312 |
.Ve |
| 313 |
.PP |
| 314 |
Here is an example that renames all c files to cpp. |
| 315 |
.PP |
| 316 |
.Vb 1 |
| 317 |
\& $ rename \*(Aq*.c\*(Aq \*(Aq#1.cpp\*(Aq |
| 318 |
.Ve |
| 319 |
.SS "A few example globmaps" |
| 320 |
.IX Subsection "A few example globmaps" |
| 321 |
Below are a few examples of globmaps |
| 322 |
.PP |
| 323 |
To copy all your .c file to a backup directory |
| 324 |
.PP |
| 325 |
.Vb 1 |
| 326 |
\& \*(Aq</my/home/*.c>\*(Aq \*(Aq</my/backup/#1.c>\*(Aq |
| 327 |
.Ve |
| 328 |
.PP |
| 329 |
If you want to compress all |
| 330 |
.PP |
| 331 |
.Vb 1 |
| 332 |
\& \*(Aq</my/home/*.[ch]>\*(Aq \*(Aq<*.gz>\*(Aq |
| 333 |
.Ve |
| 334 |
.PP |
| 335 |
To uncompress |
| 336 |
.PP |
| 337 |
.Vb 1 |
| 338 |
\& \*(Aq</my/home/*.[ch].gz>\*(Aq \*(Aq</my/home/#1.#2>\*(Aq |
| 339 |
.Ve |
| 340 |
.SH "SEE ALSO" |
| 341 |
.IX Header "SEE ALSO" |
| 342 |
File::Glob |
| 343 |
.SH AUTHOR |
| 344 |
.IX Header "AUTHOR" |
| 345 |
The \fIFile::GlobMapper\fR module was written by Paul Marquess, \[email protected]\fR. |
| 346 |
.SH "COPYRIGHT AND LICENSE" |
| 347 |
.IX Header "COPYRIGHT AND LICENSE" |
| 348 |
Copyright (c) 2005 Paul Marquess. All rights reserved. |
| 349 |
This program is free software; you can redistribute it and/or |
| 350 |
modify it under the same terms as Perl itself. |