| 1 | .\" Automatically generated by Pod::Man v1.34, Pod::Parser v1.13 |
| 2 | .\" |
| 3 | .\" Standard preamble: |
| 4 | .\" ======================================================================== |
| 5 | .de Sh \" Subsection heading |
| 6 | .br |
| 7 | .if t .Sp |
| 8 | .ne 5 |
| 9 | .PP |
| 10 | \fB\\$1\fR |
| 11 | .PP |
| 12 | .. |
| 13 | .de Sp \" Vertical space (when we can't use .PP) |
| 14 | .if t .sp .5v |
| 15 | .if n .sp |
| 16 | .. |
| 17 | .de Vb \" Begin verbatim text |
| 18 | .ft CW |
| 19 | .nf |
| 20 | .ne \\$1 |
| 21 | .. |
| 22 | .de Ve \" End verbatim text |
| 23 | .ft R |
| 24 | .fi |
| 25 | .. |
| 26 | .\" Set up some character translations and predefined strings. \*(-- will |
| 27 | .\" give an unbreakable dash, \*(PI will give pi, \*(L" will give a left |
| 28 | .\" double quote, and \*(R" will give a right double quote. | will give a |
| 29 | .\" real vertical bar. \*(C+ will give a nicer C++. Capital omega is used to |
| 30 | .\" do unbreakable dashes and therefore won't be available. \*(C` and \*(C' |
| 31 | .\" expand to `' in nroff, nothing in troff, for use with C<>. |
| 32 | .tr \(*W-|\(bv\*(Tr |
| 33 | .ds C+ C\v'-.1v'\h'-1p'\s-2+\h'-1p'+\s0\v'.1v'\h'-1p' |
| 34 | .ie n \{\ |
| 35 | . ds -- \(*W- |
| 36 | . ds PI pi |
| 37 | . if (\n(.H=4u)&(1m=24u) .ds -- \(*W\h'-12u'\(*W\h'-12u'-\" diablo 10 pitch |
| 38 | . if (\n(.H=4u)&(1m=20u) .ds -- \(*W\h'-12u'\(*W\h'-8u'-\" diablo 12 pitch |
| 39 | . ds L" "" |
| 40 | . ds R" "" |
| 41 | . ds C` "" |
| 42 | . ds C' "" |
| 43 | 'br\} |
| 44 | .el\{\ |
| 45 | . ds -- \|\(em\| |
| 46 | . ds PI \(*p |
| 47 | . ds L" `` |
| 48 | . ds R" '' |
| 49 | 'br\} |
| 50 | .\" |
| 51 | .\" If the F register is turned on, we'll generate index entries on stderr for |
| 52 | .\" titles (.TH), headers (.SH), subsections (.Sh), items (.Ip), and index |
| 53 | .\" entries marked with X<> in POD. Of course, you'll have to process the |
| 54 | .\" output yourself in some meaningful fashion. |
| 55 | .if \nF \{\ |
| 56 | . de IX |
| 57 | . tm Index:\\$1\t\\n%\t"\\$2" |
| 58 | .. |
| 59 | . nr % 0 |
| 60 | . rr F |
| 61 | .\} |
| 62 | .\" |
| 63 | .\" For nroff, turn off justification. Always turn off hyphenation; it makes |
| 64 | .\" way too many mistakes in technical documents. |
| 65 | .hy 0 |
| 66 | .if n .na |
| 67 | .\" |
| 68 | .\" Accent mark definitions (@(#)ms.acc 1.5 88/02/08 SMI; from UCB 4.2). |
| 69 | .\" Fear. Run. Save yourself. No user-serviceable parts. |
| 70 | . \" fudge factors for nroff and troff |
| 71 | .if n \{\ |
| 72 | . ds #H 0 |
| 73 | . ds #V .8m |
| 74 | . ds #F .3m |
| 75 | . ds #[ \f1 |
| 76 | . ds #] \fP |
| 77 | .\} |
| 78 | .if t \{\ |
| 79 | . ds #H ((1u-(\\\\n(.fu%2u))*.13m) |
| 80 | . ds #V .6m |
| 81 | . ds #F 0 |
| 82 | . ds #[ \& |
| 83 | . ds #] \& |
| 84 | .\} |
| 85 | . \" simple accents for nroff and troff |
| 86 | .if n \{\ |
| 87 | . ds ' \& |
| 88 | . ds ` \& |
| 89 | . ds ^ \& |
| 90 | . ds , \& |
| 91 | . ds ~ ~ |
| 92 | . ds / |
| 93 | .\} |
| 94 | .if t \{\ |
| 95 | . ds ' \\k:\h'-(\\n(.wu*8/10-\*(#H)'\'\h"|\\n:u" |
| 96 | . ds ` \\k:\h'-(\\n(.wu*8/10-\*(#H)'\`\h'|\\n:u' |
| 97 | . ds ^ \\k:\h'-(\\n(.wu*10/11-\*(#H)'^\h'|\\n:u' |
| 98 | . ds , \\k:\h'-(\\n(.wu*8/10)',\h'|\\n:u' |
| 99 | . ds ~ \\k:\h'-(\\n(.wu-\*(#H-.1m)'~\h'|\\n:u' |
| 100 | . ds / \\k:\h'-(\\n(.wu*8/10-\*(#H)'\z\(sl\h'|\\n:u' |
| 101 | .\} |
| 102 | . \" troff and (daisy-wheel) nroff accents |
| 103 | .ds : \\k:\h'-(\\n(.wu*8/10-\*(#H+.1m+\*(#F)'\v'-\*(#V'\z.\h'.2m+\*(#F'.\h'|\\n:u'\v'\*(#V' |
| 104 | .ds 8 \h'\*(#H'\(*b\h'-\*(#H' |
| 105 | .ds o \\k:\h'-(\\n(.wu+\w'\(de'u-\*(#H)/2u'\v'-.3n'\*(#[\z\(de\v'.3n'\h'|\\n:u'\*(#] |
| 106 | .ds d- \h'\*(#H'\(pd\h'-\w'~'u'\v'-.25m'\f2\(hy\fP\v'.25m'\h'-\*(#H' |
| 107 | .ds D- D\\k:\h'-\w'D'u'\v'-.11m'\z\(hy\v'.11m'\h'|\\n:u' |
| 108 | .ds th \*(#[\v'.3m'\s+1I\s-1\v'-.3m'\h'-(\w'I'u*2/3)'\s-1o\s+1\*(#] |
| 109 | .ds Th \*(#[\s+2I\s-2\h'-\w'I'u*3/5'\v'-.3m'o\v'.3m'\*(#] |
| 110 | .ds ae a\h'-(\w'a'u*4/10)'e |
| 111 | .ds Ae A\h'-(\w'A'u*4/10)'E |
| 112 | . \" corrections for vroff |
| 113 | .if v .ds ~ \\k:\h'-(\\n(.wu*9/10-\*(#H)'\s-2\u~\d\s+2\h'|\\n:u' |
| 114 | .if v .ds ^ \\k:\h'-(\\n(.wu*10/11-\*(#H)'\v'-.4m'^\v'.4m'\h'|\\n:u' |
| 115 | . \" for low resolution devices (crt and lpr) |
| 116 | .if \n(.H>23 .if \n(.V>19 \ |
| 117 | \{\ |
| 118 | . ds : e |
| 119 | . ds 8 ss |
| 120 | . ds o a |
| 121 | . ds d- d\h'-1'\(ga |
| 122 | . ds D- D\h'-1'\(hy |
| 123 | . ds th \o'bp' |
| 124 | . ds Th \o'LP' |
| 125 | . ds ae ae |
| 126 | . ds Ae AE |
| 127 | .\} |
| 128 | .rm #[ #] #H #V #F C |
| 129 | .\" ======================================================================== |
| 130 | .\" |
| 131 | .IX Title "Tie::File 3" |
| 132 | .TH Tie::File 3 "2002-06-01" "perl v5.8.0" "Perl Programmers Reference Guide" |
| 133 | .SH "NAME" |
| 134 | Tie::File \- Access the lines of a disk file via a Perl array |
| 135 | .SH "SYNOPSIS" |
| 136 | .IX Header "SYNOPSIS" |
| 137 | .Vb 1 |
| 138 | \& # This file documents Tie::File version 0.93 |
| 139 | .Ve |
| 140 | .PP |
| 141 | .Vb 1 |
| 142 | \& tie @array, 'Tie::File', filename or die ...; |
| 143 | .Ve |
| 144 | .PP |
| 145 | .Vb 2 |
| 146 | \& $array[13] = 'blah'; # line 13 of the file is now 'blah' |
| 147 | \& print $array[42]; # display line 42 of the file |
| 148 | .Ve |
| 149 | .PP |
| 150 | .Vb 2 |
| 151 | \& $n_recs = @array; # how many records are in the file? |
| 152 | \& $#array -= 2; # chop two records off the end |
| 153 | .Ve |
| 154 | .PP |
| 155 | .Vb 3 |
| 156 | \& for (@array) { |
| 157 | \& s/PERL/Perl/g; # Replace PERL with Perl everywhere in the file |
| 158 | \& } |
| 159 | .Ve |
| 160 | .PP |
| 161 | .Vb 2 |
| 162 | \& # These are just like regular push, pop, unshift, shift, and splice |
| 163 | \& # Except that they modify the file in the way you would expect |
| 164 | .Ve |
| 165 | .PP |
| 166 | .Vb 5 |
| 167 | \& push @array, new recs...; |
| 168 | \& my $r1 = pop @array; |
| 169 | \& unshift @array, new recs...; |
| 170 | \& my $r1 = shift @array; |
| 171 | \& @old_recs = splice @array, 3, 7, new recs...; |
| 172 | .Ve |
| 173 | .PP |
| 174 | .Vb 1 |
| 175 | \& untie @array; # all finished |
| 176 | .Ve |
| 177 | .SH "DESCRIPTION" |
| 178 | .IX Header "DESCRIPTION" |
| 179 | \&\f(CW\*(C`Tie::File\*(C'\fR represents a regular text file as a Perl array. Each |
| 180 | element in the array corresponds to a record in the file. The first |
| 181 | line of the file is element 0 of the array; the second line is element |
| 182 | 1, and so on. |
| 183 | .PP |
| 184 | The file is \fInot\fR loaded into memory, so this will work even for |
| 185 | gigantic files. |
| 186 | .PP |
| 187 | Changes to the array are reflected in the file immediately. |
| 188 | .PP |
| 189 | Lazy people and beginners may now stop reading the manual. |
| 190 | .ie n .Sh """recsep""" |
| 191 | .el .Sh "\f(CWrecsep\fP" |
| 192 | .IX Subsection "recsep" |
| 193 | What is a 'record'? By default, the meaning is the same as for the |
| 194 | \&\f(CW\*(C`<...>\*(C'\fR operator: It's a string terminated by \f(CW$/\fR, which is |
| 195 | probably \f(CW"\en"\fR. (Minor exception: on dos and Win32 systems, a |
| 196 | \&'record' is a string terminated by \f(CW"\er\en"\fR.) You may change the |
| 197 | definition of \*(L"record\*(R" by supplying the \f(CW\*(C`recsep\*(C'\fR option in the \f(CW\*(C`tie\*(C'\fR |
| 198 | call: |
| 199 | .PP |
| 200 | .Vb 1 |
| 201 | \& tie @array, 'Tie::File', $file, recsep => 'es'; |
| 202 | .Ve |
| 203 | .PP |
| 204 | This says that records are delimited by the string \f(CW\*(C`es\*(C'\fR. If the file |
| 205 | contained the following data: |
| 206 | .PP |
| 207 | .Vb 1 |
| 208 | \& Curse these pesky flies!\en |
| 209 | .Ve |
| 210 | .PP |
| 211 | then the \f(CW@array\fR would appear to have four elements: |
| 212 | .PP |
| 213 | .Vb 4 |
| 214 | \& "Curse th" |
| 215 | \& "e p" |
| 216 | \& "ky fli" |
| 217 | \& "!\en" |
| 218 | .Ve |
| 219 | .PP |
| 220 | An undefined value is not permitted as a record separator. Perl's |
| 221 | special \*(L"paragraph mode\*(R" semantics (A\*` la \f(CW\*(C`$/ = ""\*(C'\fR) are not |
| 222 | emulated. |
| 223 | .PP |
| 224 | Records read from the tied array do not have the record separator |
| 225 | string on the end; this is to allow |
| 226 | .PP |
| 227 | .Vb 1 |
| 228 | \& $array[17] .= "extra"; |
| 229 | .Ve |
| 230 | .PP |
| 231 | to work as expected. |
| 232 | .PP |
| 233 | (See \*(L"autochomp\*(R", below.) Records stored into the array will have |
| 234 | the record separator string appended before they are written to the |
| 235 | file, if they don't have one already. For example, if the record |
| 236 | separator string is \f(CW"\en"\fR, then the following two lines do exactly |
| 237 | the same thing: |
| 238 | .PP |
| 239 | .Vb 2 |
| 240 | \& $array[17] = "Cherry pie"; |
| 241 | \& $array[17] = "Cherry pie\en"; |
| 242 | .Ve |
| 243 | .PP |
| 244 | The result is that the contents of line 17 of the file will be |
| 245 | replaced with \*(L"Cherry pie\*(R"; a newline character will separate line 17 |
| 246 | from line 18. This means that this code will do nothing: |
| 247 | .PP |
| 248 | .Vb 1 |
| 249 | \& chomp $array[17]; |
| 250 | .Ve |
| 251 | .PP |
| 252 | Because the \f(CW\*(C`chomp\*(C'\fRed value will have the separator reattached when |
| 253 | it is written back to the file. There is no way to create a file |
| 254 | whose trailing record separator string is missing. |
| 255 | .PP |
| 256 | Inserting records that \fIcontain\fR the record separator string is not |
| 257 | supported by this module. It will probably produce a reasonable |
| 258 | result, but what this result will be may change in a future version. |
| 259 | Use 'splice' to insert records or to replace one record with several. |
| 260 | .ie n .Sh """autochomp""" |
| 261 | .el .Sh "\f(CWautochomp\fP" |
| 262 | .IX Subsection "autochomp" |
| 263 | Normally, array elements have the record separator removed, so that if |
| 264 | the file contains the text |
| 265 | .PP |
| 266 | .Vb 3 |
| 267 | \& Gold |
| 268 | \& Frankincense |
| 269 | \& Myrrh |
| 270 | .Ve |
| 271 | .PP |
| 272 | the tied array will appear to contain \f(CW\*(C`("Gold", "Frankincense", |
| 273 | "Myrrh")\*(C'\fR. If you set \f(CW\*(C`autochomp\*(C'\fR to a false value, the record |
| 274 | separator will not be removed. If the file above was tied with |
| 275 | .PP |
| 276 | .Vb 1 |
| 277 | \& tie @gifts, "Tie::File", $gifts, autochomp => 0; |
| 278 | .Ve |
| 279 | .PP |
| 280 | then the array \f(CW@gifts\fR would appear to contain \f(CW\*(C`("Gold\en", |
| 281 | "Frankincense\en", "Myrrh\en")\*(C'\fR, or (on Win32 systems) \f(CW\*(C`("Gold\er\en", |
| 282 | "Frankincense\er\en", "Myrrh\er\en")\*(C'\fR. |
| 283 | .ie n .Sh """mode""" |
| 284 | .el .Sh "\f(CWmode\fP" |
| 285 | .IX Subsection "mode" |
| 286 | Normally, the specified file will be opened for read and write access, |
| 287 | and will be created if it does not exist. (That is, the flags |
| 288 | \&\f(CW\*(C`O_RDWR | O_CREAT\*(C'\fR are supplied in the \f(CW\*(C`open\*(C'\fR call.) If you want to |
| 289 | change this, you may supply alternative flags in the \f(CW\*(C`mode\*(C'\fR option. |
| 290 | See Fcntl for a listing of available flags. |
| 291 | For example: |
| 292 | .PP |
| 293 | .Vb 3 |
| 294 | \& # open the file if it exists, but fail if it does not exist |
| 295 | \& use Fcntl 'O_RDWR'; |
| 296 | \& tie @array, 'Tie::File', $file, mode => O_RDWR; |
| 297 | .Ve |
| 298 | .PP |
| 299 | .Vb 3 |
| 300 | \& # create the file if it does not exist |
| 301 | \& use Fcntl 'O_RDWR', 'O_CREAT'; |
| 302 | \& tie @array, 'Tie::File', $file, mode => O_RDWR | O_CREAT; |
| 303 | .Ve |
| 304 | .PP |
| 305 | .Vb 3 |
| 306 | \& # open an existing file in read-only mode |
| 307 | \& use Fcntl 'O_RDONLY'; |
| 308 | \& tie @array, 'Tie::File', $file, mode => O_RDONLY; |
| 309 | .Ve |
| 310 | .PP |
| 311 | Opening the data file in write-only or append mode is not supported. |
| 312 | .ie n .Sh """memory""" |
| 313 | .el .Sh "\f(CWmemory\fP" |
| 314 | .IX Subsection "memory" |
| 315 | This is an upper limit on the amount of memory that \f(CW\*(C`Tie::File\*(C'\fR will |
| 316 | consume at any time while managing the file. This is used for two |
| 317 | things: managing the \fIread cache\fR and managing the \fIdeferred write |
| 318 | buffer\fR. |
| 319 | .PP |
| 320 | Records read in from the file are cached, to avoid having to re-read |
| 321 | them repeatedly. If you read the same record twice, the first time it |
| 322 | will be stored in memory, and the second time it will be fetched from |
| 323 | the \fIread cache\fR. The amount of data in the read cache will not |
| 324 | exceed the value you specified for \f(CW\*(C`memory\*(C'\fR. If \f(CW\*(C`Tie::File\*(C'\fR wants |
| 325 | to cache a new record, but the read cache is full, it will make room |
| 326 | by expiring the least-recently visited records from the read cache. |
| 327 | .PP |
| 328 | The default memory limit is 2Mib. You can adjust the maximum read |
| 329 | cache size by supplying the \f(CW\*(C`memory\*(C'\fR option. The argument is the |
| 330 | desired cache size, in bytes. |
| 331 | .PP |
| 332 | .Vb 2 |
| 333 | \& # I have a lot of memory, so use a large cache to speed up access |
| 334 | \& tie @array, 'Tie::File', $file, memory => 20_000_000; |
| 335 | .Ve |
| 336 | .PP |
| 337 | Setting the memory limit to 0 will inhibit caching; records will be |
| 338 | fetched from disk every time you examine them. |
| 339 | .PP |
| 340 | The \f(CW\*(C`memory\*(C'\fR value is not an absolute or exact limit on the memory |
| 341 | used. \f(CW\*(C`Tie::File\*(C'\fR objects contains some structures besides the read |
| 342 | cache and the deferred write buffer, whose sizes are not charged |
| 343 | against \f(CW\*(C`memory\*(C'\fR. |
| 344 | .ie n .Sh """dw_size""" |
| 345 | .el .Sh "\f(CWdw_size\fP" |
| 346 | .IX Subsection "dw_size" |
| 347 | (This is an advanced feature. Skip this section on first reading.) |
| 348 | .PP |
| 349 | If you use deferred writing (See \*(L"Deferred Writing\*(R", below) then |
| 350 | data you write into the array will not be written directly to the |
| 351 | file; instead, it will be saved in the \fIdeferred write buffer\fR to be |
| 352 | written out later. Data in the deferred write buffer is also charged |
| 353 | against the memory limit you set with the \f(CW\*(C`memory\*(C'\fR option. |
| 354 | .PP |
| 355 | You may set the \f(CW\*(C`dw_size\*(C'\fR option to limit the amount of data that can |
| 356 | be saved in the deferred write buffer. This limit may not exceed the |
| 357 | total memory limit. For example, if you set \f(CW\*(C`dw_size\*(C'\fR to 1000 and |
| 358 | \&\f(CW\*(C`memory\*(C'\fR to 2500, that means that no more than 1000 bytes of deferred |
| 359 | writes will be saved up. The space available for the read cache will |
| 360 | vary, but it will always be at least 1500 bytes (if the deferred write |
| 361 | buffer is full) and it could grow as large as 2500 bytes (if the |
| 362 | deferred write buffer is empty.) |
| 363 | .PP |
| 364 | If you don't specify a \f(CW\*(C`dw_size\*(C'\fR, it defaults to the entire memory |
| 365 | limit. |
| 366 | .Sh "Option Format" |
| 367 | .IX Subsection "Option Format" |
| 368 | \&\f(CW\*(C`\-mode\*(C'\fR is a synonym for \f(CW\*(C`mode\*(C'\fR. \f(CW\*(C`\-recsep\*(C'\fR is a synonym for |
| 369 | \&\f(CW\*(C`recsep\*(C'\fR. \f(CW\*(C`\-memory\*(C'\fR is a synonym for \f(CW\*(C`memory\*(C'\fR. You get the |
| 370 | idea. |
| 371 | .SH "Public Methods" |
| 372 | .IX Header "Public Methods" |
| 373 | The \f(CW\*(C`tie\*(C'\fR call returns an object, say \f(CW$o\fR. You may call |
| 374 | .PP |
| 375 | .Vb 2 |
| 376 | \& $rec = $o->FETCH($n); |
| 377 | \& $o->STORE($n, $rec); |
| 378 | .Ve |
| 379 | .PP |
| 380 | to fetch or store the record at line \f(CW$n\fR, respectively; similarly |
| 381 | the other tied array methods. (See perltie for details.) You may |
| 382 | also call the following methods on this object: |
| 383 | .ie n .Sh """flock""" |
| 384 | .el .Sh "\f(CWflock\fP" |
| 385 | .IX Subsection "flock" |
| 386 | .Vb 1 |
| 387 | \& $o->flock(MODE) |
| 388 | .Ve |
| 389 | .PP |
| 390 | will lock the tied file. \f(CW\*(C`MODE\*(C'\fR has the same meaning as the second |
| 391 | argument to the Perl built-in \f(CW\*(C`flock\*(C'\fR function; for example |
| 392 | \&\f(CW\*(C`LOCK_SH\*(C'\fR or \f(CW\*(C`LOCK_EX | LOCK_NB\*(C'\fR. (These constants are provided by |
| 393 | the \f(CW\*(C`use Fcntl ':flock'\*(C'\fR declaration.) |
| 394 | .PP |
| 395 | \&\f(CW\*(C`MODE\*(C'\fR is optional; the default is \f(CW\*(C`LOCK_EX\*(C'\fR. |
| 396 | .PP |
| 397 | \&\f(CW\*(C`Tie::File\*(C'\fR promises that the following sequence of operations will |
| 398 | be safe: |
| 399 | .PP |
| 400 | .Vb 2 |
| 401 | \& my $o = tie @array, "Tie::File", $filename; |
| 402 | \& $o->flock; |
| 403 | .Ve |
| 404 | .PP |
| 405 | In particular, \f(CW\*(C`Tie::File\*(C'\fR will \fInot\fR read or write the file during |
| 406 | the \f(CW\*(C`tie\*(C'\fR call. (Exception: Using \f(CW\*(C`mode => O_TRUNC\*(C'\fR will, of |
| 407 | course, erase the file during the \f(CW\*(C`tie\*(C'\fR call. If you want to do this |
| 408 | safely, then open the file without \f(CW\*(C`O_TRUNC\*(C'\fR, lock the file, and use |
| 409 | \&\f(CW\*(C`@array = ()\*(C'\fR.) |
| 410 | .PP |
| 411 | The best way to unlock a file is to discard the object and untie the |
| 412 | array. It is probably unsafe to unlock the file without also untying |
| 413 | it, because if you do, changes may remain unwritten inside the object. |
| 414 | That is why there is no shortcut for unlocking. If you really want to |
| 415 | unlock the file prematurely, you know what to do; if you don't know |
| 416 | what to do, then don't do it. |
| 417 | .PP |
| 418 | All the usual warnings about file locking apply here. In particular, |
| 419 | note that file locking in Perl is \fBadvisory\fR, which means that |
| 420 | holding a lock will not prevent anyone else from reading, writing, or |
| 421 | erasing the file; it only prevents them from getting another lock at |
| 422 | the same time. Locks are analogous to green traffic lights: If you |
| 423 | have a green light, that does not prevent the idiot coming the other |
| 424 | way from plowing into you sideways; it merely guarantees to you that |
| 425 | the idiot does not also have a green light at the same time. |
| 426 | .ie n .Sh """autochomp""" |
| 427 | .el .Sh "\f(CWautochomp\fP" |
| 428 | .IX Subsection "autochomp" |
| 429 | .Vb 2 |
| 430 | \& my $old_value = $o->autochomp(0); # disable autochomp option |
| 431 | \& my $old_value = $o->autochomp(1); # enable autochomp option |
| 432 | .Ve |
| 433 | .PP |
| 434 | .Vb 1 |
| 435 | \& my $ac = $o->autochomp(); # recover current value |
| 436 | .Ve |
| 437 | .PP |
| 438 | See \*(L"autochomp\*(R", above. |
| 439 | .ie n .Sh """defer""\fP, \f(CW""flush""\fP, \f(CW""discard""\fP, and \f(CW""autodefer""" |
| 440 | .el .Sh "\f(CWdefer\fP, \f(CWflush\fP, \f(CWdiscard\fP, and \f(CWautodefer\fP" |
| 441 | .IX Subsection "defer, flush, discard, and autodefer" |
| 442 | See \*(L"Deferred Writing\*(R", below. |
| 443 | .SH "Tying to an already-opened filehandle" |
| 444 | .IX Header "Tying to an already-opened filehandle" |
| 445 | If \f(CW$fh\fR is a filehandle, such as is returned by \f(CW\*(C`IO::File\*(C'\fR or one |
| 446 | of the other \f(CW\*(C`IO\*(C'\fR modules, you may use: |
| 447 | .PP |
| 448 | .Vb 1 |
| 449 | \& tie @array, 'Tie::File', $fh, ...; |
| 450 | .Ve |
| 451 | .PP |
| 452 | Similarly if you opened that handle \f(CW\*(C`FH\*(C'\fR with regular \f(CW\*(C`open\*(C'\fR or |
| 453 | \&\f(CW\*(C`sysopen\*(C'\fR, you may use: |
| 454 | .PP |
| 455 | .Vb 1 |
| 456 | \& tie @array, 'Tie::File', \e*FH, ...; |
| 457 | .Ve |
| 458 | .PP |
| 459 | Handles that were opened write-only won't work. Handles that were |
| 460 | opened read-only will work as long as you don't try to modify the |
| 461 | array. Handles must be attached to seekable sources of data\-\-\-that |
| 462 | means no pipes or sockets. If \f(CW\*(C`Tie::File\*(C'\fR can detect that you |
| 463 | supplied a non-seekable handle, the \f(CW\*(C`tie\*(C'\fR call will throw an |
| 464 | exception. (On Unix systems, it can detect this.) |
| 465 | .SH "Deferred Writing" |
| 466 | .IX Header "Deferred Writing" |
| 467 | (This is an advanced feature. Skip this section on first reading.) |
| 468 | .PP |
| 469 | Normally, modifying a \f(CW\*(C`Tie::File\*(C'\fR array writes to the underlying file |
| 470 | immediately. Every assignment like \f(CW\*(C`$a[3] = ...\*(C'\fR rewrites as much of |
| 471 | the file as is necessary; typically, everything from line 3 through |
| 472 | the end will need to be rewritten. This is the simplest and most |
| 473 | transparent behavior. Performance even for large files is reasonably |
| 474 | good. |
| 475 | .PP |
| 476 | However, under some circumstances, this behavior may be excessively |
| 477 | slow. For example, suppose you have a million-record file, and you |
| 478 | want to do: |
| 479 | .PP |
| 480 | .Vb 3 |
| 481 | \& for (@FILE) { |
| 482 | \& $_ = "> $_"; |
| 483 | \& } |
| 484 | .Ve |
| 485 | .PP |
| 486 | The first time through the loop, you will rewrite the entire file, |
| 487 | from line 0 through the end. The second time through the loop, you |
| 488 | will rewrite the entire file from line 1 through the end. The third |
| 489 | time through the loop, you will rewrite the entire file from line 2 to |
| 490 | the end. And so on. |
| 491 | .PP |
| 492 | If the performance in such cases is unacceptable, you may defer the |
| 493 | actual writing, and then have it done all at once. The following loop |
| 494 | will perform much better for large files: |
| 495 | .PP |
| 496 | .Vb 5 |
| 497 | \& (tied @a)->defer; |
| 498 | \& for (@a) { |
| 499 | \& $_ = "> $_"; |
| 500 | \& } |
| 501 | \& (tied @a)->flush; |
| 502 | .Ve |
| 503 | .PP |
| 504 | If \f(CW\*(C`Tie::File\*(C'\fR's memory limit is large enough, all the writing will |
| 505 | done in memory. Then, when you call \f(CW\*(C`\->flush\*(C'\fR, the entire file |
| 506 | will be rewritten in a single pass. |
| 507 | .PP |
| 508 | (Actually, the preceding discussion is something of a fib. You don't |
| 509 | need to enable deferred writing to get good performance for this |
| 510 | common case, because \f(CW\*(C`Tie::File\*(C'\fR will do it for you automatically |
| 511 | unless you specifically tell it not to. See \*(L"autodeferring\*(R", |
| 512 | below.) |
| 513 | .PP |
| 514 | Calling \f(CW\*(C`\->flush\*(C'\fR returns the array to immediate-write mode. If |
| 515 | you wish to discard the deferred writes, you may call \f(CW\*(C`\->discard\*(C'\fR |
| 516 | instead of \f(CW\*(C`\->flush\*(C'\fR. Note that in some cases, some of the data |
| 517 | will have been written already, and it will be too late for |
| 518 | \&\f(CW\*(C`\->discard\*(C'\fR to discard all the changes. Support for |
| 519 | \&\f(CW\*(C`\->discard\*(C'\fR may be withdrawn in a future version of \f(CW\*(C`Tie::File\*(C'\fR. |
| 520 | .PP |
| 521 | Deferred writes are cached in memory up to the limit specified by the |
| 522 | \&\f(CW\*(C`dw_size\*(C'\fR option (see above). If the deferred-write buffer is full |
| 523 | and you try to write still more deferred data, the buffer will be |
| 524 | flushed. All buffered data will be written immediately, the buffer |
| 525 | will be emptied, and the now-empty space will be used for future |
| 526 | deferred writes. |
| 527 | .PP |
| 528 | If the deferred-write buffer isn't yet full, but the total size of the |
| 529 | buffer and the read cache would exceed the \f(CW\*(C`memory\*(C'\fR limit, the oldest |
| 530 | records will be expired from the read cache until the total size is |
| 531 | under the limit. |
| 532 | .PP |
| 533 | \&\f(CW\*(C`push\*(C'\fR, \f(CW\*(C`pop\*(C'\fR, \f(CW\*(C`shift\*(C'\fR, \f(CW\*(C`unshift\*(C'\fR, and \f(CW\*(C`splice\*(C'\fR cannot be |
| 534 | deferred. When you perform one of these operations, any deferred data |
| 535 | is written to the file and the operation is performed immediately. |
| 536 | This may change in a future version. |
| 537 | .PP |
| 538 | If you resize the array with deferred writing enabled, the file will |
| 539 | be resized immediately, but deferred records will not be written. |
| 540 | This has a surprising consequence: \f(CW\*(C`@a = (...)\*(C'\fR erases the file |
| 541 | immediately, but the writing of the actual data is deferred. This |
| 542 | might be a bug. If it is a bug, it will be fixed in a future version. |
| 543 | .Sh "Autodeferring" |
| 544 | .IX Subsection "Autodeferring" |
| 545 | \&\f(CW\*(C`Tie::File\*(C'\fR tries to guess when deferred writing might be helpful, |
| 546 | and to turn it on and off automatically. |
| 547 | .PP |
| 548 | .Vb 3 |
| 549 | \& for (@a) { |
| 550 | \& $_ = "> $_"; |
| 551 | \& } |
| 552 | .Ve |
| 553 | .PP |
| 554 | In this example, only the first two assignments will be done |
| 555 | immediately; after this, all the changes to the file will be deferred |
| 556 | up to the user-specified memory limit. |
| 557 | .PP |
| 558 | You should usually be able to ignore this and just use the module |
| 559 | without thinking about deferring. However, special applications may |
| 560 | require fine control over which writes are deferred, or may require |
| 561 | that all writes be immediate. To disable the autodeferment feature, |
| 562 | use |
| 563 | .PP |
| 564 | .Vb 1 |
| 565 | \& (tied @o)->autodefer(0); |
| 566 | .Ve |
| 567 | .PP |
| 568 | or |
| 569 | .PP |
| 570 | .Vb 1 |
| 571 | \& tie @array, 'Tie::File', $file, autodefer => 0; |
| 572 | .Ve |
| 573 | .PP |
| 574 | Similarly, \f(CW\*(C`\->autodefer(1)\*(C'\fR re-enables autodeferment, and |
| 575 | \&\f(CW\*(C`\->autodefer()\*(C'\fR recovers the current value of the autodefer setting. |
| 576 | .SH "CAVEATS" |
| 577 | .IX Header "CAVEATS" |
| 578 | (That's Latin for 'warnings'.) |
| 579 | .IP "\(bu" 4 |
| 580 | This is \s-1BETA\s0 \s-1RELEASE\s0 \s-1SOFTWARE\s0. It may have bugs. See the discussion |
| 581 | below about the (lack of any) warranty. |
| 582 | .Sp |
| 583 | In particular, this means that the interface may change in |
| 584 | incompatible ways from one version to the next, without warning. That |
| 585 | has happened at least once already. The interface will freeze before |
| 586 | Perl 5.8 is released, probably sometime in April 2002. |
| 587 | .IP "\(bu" 4 |
| 588 | Reasonable effort was made to make this module efficient. Nevertheless, |
| 589 | changing the size of a record in the middle of a large file will |
| 590 | always be fairly slow, because everything after the new record must be |
| 591 | moved. |
| 592 | .IP "\(bu" 4 |
| 593 | The behavior of tied arrays is not precisely the same as for regular |
| 594 | arrays. For example: |
| 595 | .Sp |
| 596 | .Vb 2 |
| 597 | \& # This DOES print "How unusual!" |
| 598 | \& undef $a[10]; print "How unusual!\en" if defined $a[10]; |
| 599 | .Ve |
| 600 | .Sp |
| 601 | \&\f(CW\*(C`undef\*(C'\fR\-ing a \f(CW\*(C`Tie::File\*(C'\fR array element just blanks out the |
| 602 | corresponding record in the file. When you read it back again, you'll |
| 603 | get the empty string, so the supposedly\-\f(CW\*(C`undef\*(C'\fR'ed value will be |
| 604 | defined. Similarly, if you have \f(CW\*(C`autochomp\*(C'\fR disabled, then |
| 605 | .Sp |
| 606 | .Vb 3 |
| 607 | \& # This DOES print "How unusual!" if 'autochomp' is disabled |
| 608 | \& undef $a[10]; |
| 609 | \& print "How unusual!\en" if $a[10]; |
| 610 | .Ve |
| 611 | .Sp |
| 612 | Because when \f(CW\*(C`autochomp\*(C'\fR is disabled, \f(CW$a[10]\fR will read back as |
| 613 | \&\f(CW"\en"\fR (or whatever the record separator string is.) |
| 614 | .Sp |
| 615 | There are other minor differences, particularly regarding \f(CW\*(C`exists\*(C'\fR |
| 616 | and \f(CW\*(C`delete\*(C'\fR, but in general, the correspondence is extremely close. |
| 617 | .IP "\(bu" 4 |
| 618 | Not quite every effort was made to make this module as efficient as |
| 619 | possible. \f(CW\*(C`FETCHSIZE\*(C'\fR should use binary search instead of linear |
| 620 | search. |
| 621 | .Sp |
| 622 | The performance of the \f(CW\*(C`flush\*(C'\fR method could be improved. At present, |
| 623 | it still rewrites the tail of the file once for each block of |
| 624 | contiguous lines to be changed. In the typical case, this will result |
| 625 | in only one rewrite, but in peculiar cases it might be bad. It should |
| 626 | be possible to perform \fIall\fR deferred writing with a single rewrite. |
| 627 | .Sp |
| 628 | Profiling suggests that these defects are probably minor; in any |
| 629 | event, they will be fixed in a future version of the module. |
| 630 | .IP "\(bu" 4 |
| 631 | I have supposed that since this module is concerned with file I/O, |
| 632 | almost all normal use of it will be heavily I/O bound. This means |
| 633 | that the time to maintain complicated data structures inside the |
| 634 | module will be dominated by the time to actually perform the I/O. |
| 635 | When there was an opportunity to spend \s-1CPU\s0 time to avoid doing I/O, I |
| 636 | tried to take it. |
| 637 | .IP "\(bu" 4 |
| 638 | You might be tempted to think that deferred writing is like |
| 639 | transactions, with \f(CW\*(C`flush\*(C'\fR as \f(CW\*(C`commit\*(C'\fR and \f(CW\*(C`discard\*(C'\fR as |
| 640 | \&\f(CW\*(C`rollback\*(C'\fR, but it isn't, so don't. |
| 641 | .SH "SUBCLASSING" |
| 642 | .IX Header "SUBCLASSING" |
| 643 | This version promises absolutely nothing about the internals, which |
| 644 | may change without notice. A future version of the module will have a |
| 645 | well-defined and stable subclassing \s-1API\s0. |
| 646 | .ie n .SH "WHAT ABOUT ""DB_File""?" |
| 647 | .el .SH "WHAT ABOUT \f(CWDB_File\fP?" |
| 648 | .IX Header "WHAT ABOUT DB_File?" |
| 649 | People sometimes point out that DB_File will do something similar, |
| 650 | and ask why \f(CW\*(C`Tie::File\*(C'\fR module is necessary. |
| 651 | .PP |
| 652 | There are a number of reasons that you might prefer \f(CW\*(C`Tie::File\*(C'\fR. |
| 653 | A list is available at \f(CW\*(C`http://perl.plover.com/TieFile/why\-not\-DB_File\*(C'\fR. |
| 654 | .SH "AUTHOR" |
| 655 | .IX Header "AUTHOR" |
| 656 | Mark Jason Dominus |
| 657 | .PP |
| 658 | To contact the author, send email to: \f(CW\*(C`mjd\-perl\-tiefile+@plover.com\*(C'\fR |
| 659 | .PP |
| 660 | To receive an announcement whenever a new version of this module is |
| 661 | released, send a blank email message to |
| 662 | \&\f(CW\*(C`mjd\-perl\-tiefile\-subscribe@plover.com\*(C'\fR. |
| 663 | .PP |
| 664 | The most recent version of this module, including documentation and |
| 665 | any news of importance, will be available at |
| 666 | .PP |
| 667 | .Vb 1 |
| 668 | \& http://perl.plover.com/TieFile/ |
| 669 | .Ve |
| 670 | .SH "LICENSE" |
| 671 | .IX Header "LICENSE" |
| 672 | \&\f(CW\*(C`Tie::File\*(C'\fR version 0.93 is copyright (C) 2002 Mark Jason Dominus. |
| 673 | .PP |
| 674 | This library is free software; you may redistribute it and/or modify |
| 675 | it under the same terms as Perl itself. |
| 676 | .PP |
| 677 | These terms are your choice of any of (1) the Perl Artistic Licence, |
| 678 | or (2) version 2 of the \s-1GNU\s0 General Public License as published by the |
| 679 | Free Software Foundation, or (3) any later version of the \s-1GNU\s0 General |
| 680 | Public License. |
| 681 | .PP |
| 682 | This library is distributed in the hope that it will be useful, |
| 683 | but \s-1WITHOUT\s0 \s-1ANY\s0 \s-1WARRANTY\s0; without even the implied warranty of |
| 684 | \&\s-1MERCHANTABILITY\s0 or \s-1FITNESS\s0 \s-1FOR\s0 A \s-1PARTICULAR\s0 \s-1PURPOSE\s0. See the |
| 685 | \&\s-1GNU\s0 General Public License for more details. |
| 686 | .PP |
| 687 | You should have received a copy of the \s-1GNU\s0 General Public License |
| 688 | along with this library program; it should be in the file \f(CW\*(C`COPYING\*(C'\fR. |
| 689 | If not, write to the Free Software Foundation, Inc., 59 Temple Place, |
| 690 | Suite 330, Boston, \s-1MA\s0 02111 \s-1USA\s0 |
| 691 | .PP |
| 692 | For licensing inquiries, contact the author at: |
| 693 | .PP |
| 694 | .Vb 3 |
| 695 | \& Mark Jason Dominus |
| 696 | \& 255 S. Warnock St. |
| 697 | \& Philadelphia, PA 19107 |
| 698 | .Ve |
| 699 | .SH "WARRANTY" |
| 700 | .IX Header "WARRANTY" |
| 701 | \&\f(CW\*(C`Tie::File\*(C'\fR version 0.93 comes with \s-1ABSOLUTELY\s0 \s-1NO\s0 \s-1WARRANTY\s0. |
| 702 | For details, see the license. |
| 703 | .SH "THANKS" |
| 704 | .IX Header "THANKS" |
| 705 | Gigantic thanks to Jarkko Hietaniemi, for agreeing to put this in the |
| 706 | core when I hadn't written it yet, and for generally being helpful, |
| 707 | supportive, and competent. (Usually the rule is \*(L"choose any one.\*(R") |
| 708 | Also big thanks to Abhijit Menon-Sen for all of the same things. |
| 709 | .PP |
| 710 | Special thanks to Craig Berry and Peter Prymmer (for \s-1VMS\s0 portability |
| 711 | help), Randy Kobes (for Win32 portability help), Clinton Pierce and |
| 712 | Autrijus Tang (for heroic eleventh-hour Win32 testing above and beyond |
| 713 | the call of duty), Michael G Schwern (for testing advice), and the |
| 714 | rest of the \s-1CPAN\s0 testers (for testing generally). |
| 715 | .PP |
| 716 | Additional thanks to: |
| 717 | Edward Avis / |
| 718 | Gerrit Haase / |
| 719 | Nikola Knezevic / |
| 720 | Nick Ing-Simmons / |
| 721 | Tassilo von Parseval / |
| 722 | H. Dieter Pearcey / |
| 723 | Slaven Rezic / |
| 724 | Peter Scott / |
| 725 | Peter Somu / |
| 726 | Autrijus Tang (again) / |
| 727 | Tels / |
| 728 | Juerd Wallboer |
| 729 | .SH "TODO" |
| 730 | .IX Header "TODO" |
| 731 | More tests. (The cache and heap modules need more unit tests.) |
| 732 | .PP |
| 733 | Improve \s-1SPLICE\s0 algorithm to use deferred writing machinery. |
| 734 | .PP |
| 735 | Cleverer strategy for flushing deferred writes. |
| 736 | .PP |
| 737 | More tests. (Stuff I didn't think of yet.) |
| 738 | .PP |
| 739 | Paragraph mode? |
| 740 | .PP |
| 741 | Fixed-length mode. Leave-blanks mode. |
| 742 | .PP |
| 743 | Maybe an autolocking mode? |
| 744 | .PP |
| 745 | Record locking with \fIfcntl()\fR? Then the module might support an undo |
| 746 | log and get real transactions. What a tour de force that would be. |
| 747 | .PP |
| 748 | More tests. |