3 perlapio - perl's IO abstraction interface.
7 #define PERLIO_NOT_STDIO 0 /* For co-existence with stdio only */
8 #include <perlio.h> /* Usually via #include <perl.h> */
10 PerlIO *PerlIO_stdin(void);
11 PerlIO *PerlIO_stdout(void);
12 PerlIO *PerlIO_stderr(void);
14 PerlIO *PerlIO_open(const char *path,const char *mode);
15 PerlIO *PerlIO_fdopen(int fd, const char *mode);
16 PerlIO *PerlIO_reopen(const char *path, const char *mode, PerlIO *old); /* deprecated */
17 int PerlIO_close(PerlIO *f);
19 int PerlIO_stdoutf(const char *fmt,...)
20 int PerlIO_puts(PerlIO *f,const char *string);
21 int PerlIO_putc(PerlIO *f,int ch);
22 int PerlIO_write(PerlIO *f,const void *buf,size_t numbytes);
23 int PerlIO_printf(PerlIO *f, const char *fmt,...);
24 int PerlIO_vprintf(PerlIO *f, const char *fmt, va_list args);
25 int PerlIO_flush(PerlIO *f);
27 int PerlIO_eof(PerlIO *f);
28 int PerlIO_error(PerlIO *f);
29 void PerlIO_clearerr(PerlIO *f);
31 int PerlIO_getc(PerlIO *d);
32 int PerlIO_ungetc(PerlIO *f,int ch);
33 int PerlIO_read(PerlIO *f, void *buf, size_t numbytes);
35 int PerlIO_fileno(PerlIO *f);
37 void PerlIO_setlinebuf(PerlIO *f);
39 Off_t PerlIO_tell(PerlIO *f);
40 int PerlIO_seek(PerlIO *f, Off_t offset, int whence);
41 void PerlIO_rewind(PerlIO *f);
43 int PerlIO_getpos(PerlIO *f, SV *save); /* prototype changed */
44 int PerlIO_setpos(PerlIO *f, SV *saved); /* prototype changed */
46 int PerlIO_fast_gets(PerlIO *f);
47 int PerlIO_has_cntptr(PerlIO *f);
48 int PerlIO_get_cnt(PerlIO *f);
49 char *PerlIO_get_ptr(PerlIO *f);
50 void PerlIO_set_ptrcnt(PerlIO *f, char *ptr, int count);
52 int PerlIO_canset_cnt(PerlIO *f); /* deprecated */
53 void PerlIO_set_cnt(PerlIO *f, int count); /* deprecated */
55 int PerlIO_has_base(PerlIO *f);
56 char *PerlIO_get_base(PerlIO *f);
57 int PerlIO_get_bufsiz(PerlIO *f);
59 PerlIO *PerlIO_importFILE(FILE *stdio, int flags);
60 FILE *PerlIO_exportFILE(PerlIO *f, int flags);
61 FILE *PerlIO_findFILE(PerlIO *f);
62 void PerlIO_releaseFILE(PerlIO *f,FILE *stdio);
64 int PerlIO_apply_layers(PerlIO *f, const char *mode, const char *layers);
65 int PerlIO_binmode(PerlIO *f, int ptype, int imode, const char *layers);
66 void PerlIO_debug(const char *fmt,...)
70 Perl's source code, and extensions that want maximum portability,
71 should use the above functions instead of those defined in ANSI C's
72 I<stdio.h>. The perl headers (in particular "perlio.h") will
73 C<#define> them to the I/O mechanism selected at Configure time.
75 The functions are modeled on those in I<stdio.h>, but parameter order
76 has been "tidied up a little".
78 C<PerlIO *> takes the place of FILE *. Like FILE * it should be
79 treated as opaque (it is probably safe to assume it is a pointer to
82 There are currently three implementations:
88 All above are #define'd to stdio functions or are trivial wrapper
89 functions which call stdio. In this case I<only> PerlIO * is a FILE *.
90 This has been the default implementation since the abstraction was
91 introduced in perl5.003_02.
95 A "legacy" implementation in terms of the "sfio" library. Used for
96 some specialist applications on Unix machines ("sfio" is not widely
97 ported away from Unix). Most of above are #define'd to the sfio
98 functions. PerlIO * is in this case Sfio_t *.
102 Introduced just after perl5.7.0, this is a re-implementation of the
103 above abstraction which allows perl more control over how IO is done
104 as it decouples IO from the way the operating system and C library
105 choose to do things. For USE_PERLIO PerlIO * has an extra layer of
106 indirection - it is a pointer-to-a-pointer. This allows the PerlIO *
107 to remain with a known value while swapping the implementation around
108 underneath I<at run time>. In this case all the above are true (but
109 very simple) functions which call the underlying implementation.
111 This is the only implementation for which C<PerlIO_apply_layers()>
112 does anything "interesting".
114 The USE_PERLIO implementation is described in L<perliol>.
118 Because "perlio.h" is a thin layer (for efficiency) the semantics of
119 these functions are somewhat dependent on the underlying implementation.
120 Where these variations are understood they are noted below.
122 Unless otherwise noted, functions return 0 on success, or a negative
123 value (usually C<EOF> which is usually -1) and set C<errno> on error.
127 =item B<PerlIO_stdin()>, B<PerlIO_stdout()>, B<PerlIO_stderr()>
129 Use these rather than C<stdin>, C<stdout>, C<stderr>. They are written
130 to look like "function calls" rather than variables because this makes
131 it easier to I<make them> function calls if platform cannot export data
132 to loaded modules, or if (say) different "threads" might have different
135 =item B<PerlIO_open(path, mode)>, B<PerlIO_fdopen(fd,mode)>
137 These correspond to fopen()/fdopen() and the arguments are the same.
138 Return C<NULL> and set C<errno> if there is an error. There may be an
139 implementation limit on the number of open handles, which may be lower
140 than the limit on the number of open files - C<errno> may not be set
141 when C<NULL> is returned if this limit is exceeded.
143 =item B<PerlIO_reopen(path,mode,f)>
145 While this currently exists in all three implementations perl itself
146 does not use it. I<As perl does not use it, it is not well tested.>
148 Perl prefers to C<dup> the new low-level descriptor to the descriptor
149 used by the existing PerlIO. This may become the behaviour of this
150 function in the future.
152 =item B<PerlIO_printf(f,fmt,...)>, B<PerlIO_vprintf(f,fmt,a)>
154 These are fprintf()/vfprintf() equivalents.
156 =item B<PerlIO_stdoutf(fmt,...)>
158 This is printf() equivalent. printf is #defined to this function,
159 so it is (currently) legal to use C<printf(fmt,...)> in perl sources.
161 =item B<PerlIO_read(f,buf,count)>, B<PerlIO_write(f,buf,count)>
163 These correspond to fread() and fwrite(). Note that arguments are
164 different, there is only one "count" and order has "file"
165 first. Returns a byte count if successful (which may be zero), returns
166 negative value and sets C<errno> on error. Depending on
167 implementation C<errno> may be C<EINTR> if operation was interrupted
170 =item B<PerlIO_close(f)>
172 Depending on implementation C<errno> may be C<EINTR> if operation was
173 interrupted by a signal.
175 =item B<PerlIO_puts(f,s)>, B<PerlIO_putc(f,c)>
177 These correspond to fputs() and fputc().
178 Note that arguments have been revised to have "file" first.
180 =item B<PerlIO_ungetc(f,c)>
182 This corresponds to ungetc(). Note that arguments have been revised
183 to have "file" first. Arranges that next read operation will return
184 the byte B<c>. Despite the implied "character" in the name only
185 values in the range 0..0xFF are defined. Returns the byte B<c> on
186 success or -1 (C<EOF>) on error. The number of bytes that can be
187 "pushed back" may vary, only 1 character is certain, and then only if
188 it is the last character that was read from the handle.
190 =item B<PerlIO_getc(f)>
192 This corresponds to getc().
193 Despite the c in the name only byte range 0..0xFF is supported.
194 Returns the character read or -1 (C<EOF>) on error.
196 =item B<PerlIO_eof(f)>
198 This corresponds to feof(). Returns a true/false indication of
199 whether the handle is at end of file. For terminal devices this may
200 or may not be "sticky" depending on the implementation. The flag is
201 cleared by PerlIO_seek(), or PerlIO_rewind().
203 =item B<PerlIO_error(f)>
205 This corresponds to ferror(). Returns a true/false indication of
206 whether there has been an IO error on the handle.
208 =item B<PerlIO_fileno(f)>
210 This corresponds to fileno(), note that on some platforms, the meaning
211 of "fileno" may not match Unix. Returns -1 if the handle has no open
212 descriptor associated with it.
214 =item B<PerlIO_clearerr(f)>
216 This corresponds to clearerr(), i.e., clears 'error' and (usually)
217 'eof' flags for the "stream". Does not return a value.
219 =item B<PerlIO_flush(f)>
221 This corresponds to fflush(). Sends any buffered write data to the
222 underlying file. If called with C<NULL> this may flush all open
223 streams (or core dump). Calling on a handle open for read only, or on
224 which last operation was a read of some kind may lead to undefined
227 =item B<PerlIO_seek(f,offset,whence)>
229 This corresponds to fseek(). Sends buffered write data to the
230 underlying file, or discards any buffered read data, then positions
231 the file desciptor as specified by B<offset> and B<whence> (sic).
232 This is the correct thing to do when switching between read and write
233 on the same handle (see issues with PerlIO_flush() above). Offset is
234 of type C<Off_t> which is a perl Configure value which may not be same
237 =item B<PerlIO_tell(f)>
239 This corresponds to ftell(). Returns the current file position, or
240 (Off_t) -1 on error. May just return value system "knows" without
241 making a system call or checking the underlying file descriptor (so
242 use on shared file descriptors is not safe without a
243 PerlIO_seek()). Return value is of type C<Off_t> which is a perl
244 Configure value which may not be same as stdio's C<off_t>.
246 =item B<PerlIO_getpos(f,p)>, B<PerlIO_setpos(f,p)>
248 These correspond (loosely) to fgetpos() and fsetpos(). Rather than
249 stdio's Fpos_t they expect a "Perl Scalar Value" to be passed. What is
250 stored there should be considered opaque. The layout of the data may
251 vary from handle to handle. When not using stdio or if platform does
252 not have the stdio calls then they are implemented in terms of
253 PerlIO_tell() and PerlIO_seek().
255 =item B<PerlIO_rewind(f)>
257 This corresponds to rewind(). It is usually defined as being
259 PerlIO_seek(f,(Off_t)0L, SEEK_SET);
262 =item B<PerlIO_tmpfile()>
264 This corresponds to tmpfile(), i.e., returns an anonymous PerlIO or
265 NULL on error. The system will attempt to automatically delete the
266 file when closed. On Unix the file is usually C<unlink>-ed just after
267 it is created so it does not matter how it gets closed. On other
268 systems the file may only be deleted if closed via PerlIO_close()
269 and/or the program exits via C<exit>. Depending on the implementation
270 there may be "race conditions" which allow other processes access to
271 the file, though in general it will be safer in this regard than
274 =item B<PerlIO_setlinebuf(f)>
276 This corresponds to setlinebuf(). Does not return a value. What
277 constitutes a "line" is implementation dependent but usually means
278 that writing "\n" flushes the buffer. What happens with things like
279 "this\nthat" is uncertain. (Perl core uses it I<only> when "dumping";
280 it has nothing to do with $| auto-flush.)
284 =head2 Co-existence with stdio
286 There is outline support for co-existence of PerlIO with stdio.
287 Obviously if PerlIO is implemented in terms of stdio there is no
288 problem. However in other cases then mechanisms must exist to create a
289 FILE * which can be passed to library code which is going to use stdio
292 The first step is to add this line:
294 #define PERLIO_NOT_STDIO 0
296 I<before> including any perl header files. (This will probably become
297 the default at some point). That prevents "perlio.h" from attempting
298 to #define stdio functions onto PerlIO functions.
300 XS code is probably better using "typemap" if it expects FILE *
301 arguments. The standard typemap will be adjusted to comprehend any
302 changes in this area.
306 =item B<PerlIO_importFILE(f,flags)>
308 Used to get a PerlIO * from a FILE *. May need additional arguments,
309 interface under review.
311 The flags argument was meant to be used for read vs write vs
312 read/write information. In hindsight it would have been better to make
313 it a char *mode as in fopen/freopen.
315 =item B<PerlIO_exportFILE(f,flags)>
317 Given a PerlIO * return a 'native' FILE * suitable for passing to code
318 expecting to be compiled and linked with ANSI C I<stdio.h>.
320 The fact that such a FILE * has been 'exported' is recorded, and may
321 affect future PerlIO operations on the original PerlIO *.
323 =item B<PerlIO_findFILE(f)>
325 Returns previously 'exported' FILE * (if any). Placeholder until
326 interface is fully defined.
328 =item B<PerlIO_releaseFILE(p,f)>
330 Calling PerlIO_releaseFILE informs PerlIO that all use of FILE * is
331 complete. It is removed from list of 'exported' FILE *s, and
332 associated PerlIO * should revert to original behaviour.
336 =head2 "Fast gets" Functions
338 In addition to standard-like API defined so far above there is an
339 "implementation" interface which allows perl to get at internals of
340 PerlIO. The following calls correspond to the various FILE_xxx macros
341 determined by Configure - or their equivalent in other
342 implementations. This section is really of interest to only those
343 concerned with detailed perl-core behaviour, implementing a PerlIO
344 mapping or writing code which can make use of the "read ahead" that
345 has been done by the IO system in the same way perl does. Note that
346 any code that uses these interfaces must be prepared to do things the
347 traditional way if a handle does not support them.
351 =item B<PerlIO_fast_gets(f)>
353 Returns true if implementation has all the interfaces required to
354 allow perl's C<sv_gets> to "bypass" normal IO mechanism.
355 This can vary from handle to handle.
357 PerlIO_fast_gets(f) = PerlIO_has_cntptr(f) && \
358 PerlIO_canset_cnt(f) && \
359 `Can set pointer into buffer'
362 =item B<PerlIO_has_cntptr(f)>
364 Implementation can return pointer to current position in the "buffer"
365 and a count of bytes available in the buffer. Do not use this - use
368 =item B<PerlIO_get_cnt(f)>
370 Return count of readable bytes in the buffer. Zero or negative return
371 means no more bytes available.
373 =item B<PerlIO_get_ptr(f)>
375 Return pointer to next readable byte in buffer, accessing via the
376 pointer (dereferencing) is only safe if PerlIO_get_cnt() has returned
377 a positive value. Only positive offsets up to value returned by
378 PerlIO_get_cnt() are allowed.
380 =item B<PerlIO_set_ptrcnt(f,p,c)>
382 Set pointer into buffer, and a count of bytes still in the
383 buffer. Should be used only to set pointer to within range implied by
384 previous calls to C<PerlIO_get_ptr> and C<PerlIO_get_cnt>. The two
385 values I<must> be consistent with each other (implementation may only
386 use one or the other or may require both).
388 =item B<PerlIO_canset_cnt(f)>
390 Implementation can adjust its idea of number of bytes in the buffer.
391 Do not use this - use PerlIO_fast_gets.
393 =item B<PerlIO_set_cnt(f,c)>
395 Obscure - set count of bytes in the buffer. Deprecated. Only usable
396 if PerlIO_canset_cnt() returns true. Currently used in only doio.c to
397 force count less than -1 to -1. Perhaps should be PerlIO_set_empty or
398 similar. This call may actually do nothing if "count" is deduced from
399 pointer and a "limit". Do not use this - use PerlIO_set_ptrcnt().
401 =item B<PerlIO_has_base(f)>
403 Returns true if implementation has a buffer, and can return pointer
404 to whole buffer and its size. Used by perl for B<-T> / B<-B> tests.
405 Other uses would be very obscure...
407 =item B<PerlIO_get_base(f)>
409 Return I<start> of buffer. Access only positive offsets in the buffer
410 up to the value returned by PerlIO_get_bufsiz().
412 =item B<PerlIO_get_bufsiz(f)>
414 Return the I<total number of bytes> in the buffer, this is neither the
415 number that can be read, nor the amount of memory allocated to the
416 buffer. Rather it is what the operating system and/or implementation
417 happened to C<read()> (or whatever) last time IO was requested.
421 =head2 Other Functions
425 =item PerlIO_apply_layers(f,mode,layers)
427 The new interface to the USE_PERLIO implementation. The layers ":crlf"
428 and ":raw" are only ones allowed for other implementations and those
429 are silently ignored. Use PerlIO_binmode() below for the portable
432 =item PerlIO_binmode(f,ptype,imode,layers)
434 The hook used by perl's C<binmode> operator.
435 B<ptype> is perl's character for the kind of IO:
447 B<imode> is C<O_BINARY> or C<O_TEXT>.
449 B<layers> is a string of layers to apply, only ":raw" or :"crlf" make
450 sense in the non USE_PERLIO case.
454 PerlIO_binmode(f,ptype,O_BINARY,":raw");
456 PerlIO_binmode(f,ptype,O_TEXT,":crlf");
458 On Unix these calls probably have no effect whatsoever. Elsewhere
459 they alter "\n" to CR,LF translation and possibly cause a special text
460 "end of file" indicator to be written or honoured on read. The effect
461 of making the call after doing any IO to the handle depends on the
462 implementation. (It may be ignored, affect any data which is already
463 buffered as well, or only apply to subsequent data.)
465 =item PerlIO_debug(fmt,...)
467 PerlIO_debug is a printf()-like function which can be used for
468 debugging. No return value. Its main use is inside PerlIO where using
469 real printf, warn() etc. would recursively call PerlIO and be a
472 PerlIO_debug writes to the file named by $ENV{'PERLIO_DEBUG'} typical
475 Bourne shells (sh, ksh, bash, zsh, ash, ...):
476 PERLIO_DEBUG=/dev/tty ./perl somescript some args
479 setenv PERLIO_DEBUG /dev/tty
480 ./perl somescript some args
482 If you have the "env" utility:
483 env PERLIO_DEBUG=/dev/tty ./perl somescript some args
487 perl somescript some args
489 If $ENV{'PERLIO_DEBUG'} is not set PerlIO_debug() is a no-op.