From: Uri Guttman Date: Sat, 16 Apr 2011 07:17:17 +0000 (-0400) Subject: added prepend_file X-Git-Url: http://git.shadowcat.co.uk/gitweb/gitweb.cgi?a=commitdiff_plain;h=b3b7ff4ed8b9fb7172af774b2b898e2027bc3650;p=urisagit%2FFile-Slurp.git added prepend_file read_file takes optional hash ref for opts read_dir takes optional hash ref for opts fixed bug with array_ref in list context fixed many open bugs pod cleanup --- diff --git a/lib/File/Slurp.pm b/lib/File/Slurp.pm index 965a492..e669350 100755 --- a/lib/File/Slurp.pm +++ b/lib/File/Slurp.pm @@ -5,22 +5,24 @@ my $printed ; use strict; use Carp ; +use Exporter ; use Fcntl qw( :DEFAULT ) ; use POSIX qw( :fcntl_h ) ; use Symbol ; +use UNIVERSAL ; -use base 'Exporter' ; -use vars qw( %EXPORT_TAGS @EXPORT_OK $VERSION @EXPORT ) ; +use vars qw( @ISA %EXPORT_TAGS @EXPORT_OK $VERSION @EXPORT ) ; +@ISA = qw( Exporter ) ; %EXPORT_TAGS = ( 'all' => [ qw( read_file write_file overwrite_file append_file read_dir ) ] ) ; @EXPORT = ( @{ $EXPORT_TAGS{'all'} } ); -@EXPORT_OK = qw( slurp ) ; +@EXPORT_OK = qw( slurp prepend_file ) ; -$VERSION = '9999.14'; +$VERSION = '9999.15'; -our $max_fast_slurp_size = 1024 * 100 ; +my $max_fast_slurp_size = 1024 * 100 ; my $is_win32 = $^O =~ /win32/i ; @@ -77,16 +79,17 @@ BEGIN { sub read_file { - my( $file_name, %args ) = @_ ; + my $file_name = shift ; + my $opts = ( ref $_[0] eq 'HASH' ) ? shift : { @_ } ; if ( !ref $file_name && 0 && - -e $file_name && -s _ < $max_fast_slurp_size && ! %args && !wantarray ) { + -e $file_name && -s _ < $max_fast_slurp_size && ! %{$opts} && !wantarray ) { local( *FH ) ; unless( open( FH, $file_name ) ) { - @_ = ( \%args, "read_file '$file_name' - sysopen: $!"); + @_ = ( $opts, "read_file '$file_name' - sysopen: $!"); goto &_error ; } @@ -96,7 +99,7 @@ sub read_file { # handle the read error - @_ = ( \%args, + @_ = ( $opts, "read_file '$file_name' - small sysread: $!"); goto &_error ; } @@ -108,50 +111,46 @@ sub read_file { # string my $buf ; - my $buf_ref = $args{'buf_ref'} || \$buf ; + my $buf_ref = $opts->{'buf_ref'} || \$buf ; ${$buf_ref} = '' ; my( $read_fh, $size_left, $blk_size ) ; -# check if we are reading from a handle (glob ref or IO:: object) +# deal with ref for a file name +# it could be an open handle or an overloaded object if ( ref $file_name ) { -# slurping a handle so use it and don't open anything. -# set the block size so we know it is a handle and read that amount + my $ref_result = _check_ref( $file_name ) ; - $read_fh = $file_name ; - $blk_size = $args{'blk_size'} || 1024 * 1024 ; - $size_left = $blk_size ; + if ( ref $ref_result ) { -# DEEP DARK MAGIC. this checks the UNTAINT IO flag of a -# glob/handle. only the DATA handle is untainted (since it is from -# trusted data in the source file). this allows us to test if this is -# the DATA handle and then to do a sysseek to make sure it gets -# slurped correctly. on some systems, the buffered i/o pointer is not -# left at the same place as the fd pointer. this sysseek makes them -# the same so slurping with sysread will work. - - eval{ require B } ; +# we got an error, deal with it - if ( $@ ) { - - @_ = ( \%args, <IO->IoFLAGS & 16 ) { + if ( $ref_result ) { -# set the seek position to the current tell. +# we got an overloaded object and the result is the stringified value +# use it as the file name + + $file_name = $ref_result ; + } + else { + +# here we have just an open handle. set $read_fh so we don't do a sysopen - sysseek( $read_fh, tell( $read_fh ), SEEK_SET ) || - croak "sysseek $!" ; + $read_fh = $file_name ; + $blk_size = $opts->{'blk_size'} || 1024 * 1024 ; + $size_left = $blk_size ; } } - else { + +# see if we have a path we need to open + + unless ( $read_fh ) { # a regular file. set the sysopen mode @@ -163,11 +162,11 @@ ERR $read_fh = gensym ; unless ( sysopen( $read_fh, $file_name, $mode ) ) { - @_ = ( \%args, "read_file '$file_name' - sysopen: $!"); + @_ = ( $opts, "read_file '$file_name' - sysopen: $!"); goto &_error ; } - if ( my $binmode = $args{'binmode'} ) { + if ( my $binmode = $opts->{'binmode'} ) { binmode( $read_fh, $binmode ) ; } @@ -183,13 +182,13 @@ ERR unless( $size_left ) { - $blk_size = $args{'blk_size'} || 1024 * 1024 ; + $blk_size = $opts->{'blk_size'} || 1024 * 1024 ; $size_left = $blk_size ; } } -# if ( $size_left < 10000 && keys %args == 0 && !wantarray ) { +# if ( $size_left < 10000 && keys %{$opts} == 0 && !wantarray ) { # #print "OPT\n" and $printed++ unless $printed ; @@ -199,7 +198,7 @@ ERR # # handle the read error -# @_ = ( \%args, "read_file '$file_name' - small2 sysread: $!"); +# @_ = ( $opts, "read_file '$file_name' - small2 sysread: $!"); # goto &_error ; # } @@ -219,7 +218,7 @@ ERR # handle the read error - @_ = ( \%args, "read_file '$file_name' - loop sysread: $!"); + @_ = ( $opts, "read_file '$file_name' - loop sysread: $!"); goto &_error ; } @@ -239,7 +238,7 @@ ERR # fix up cr/lf to be a newline if this is a windows text file - ${$buf_ref} =~ s/\015\012/\n/g if $is_win32 && !$args{'binmode'} ; + ${$buf_ref} =~ s/\015\012/\n/g if $is_win32 && !$opts->{'binmode'} ; # this is the 5 returns in a row. each handles one possible # combination of caller context and requested return type @@ -247,24 +246,29 @@ ERR my $sep = $/ ; $sep = '\n\n+' if defined $sep && $sep eq '' ; -# caller wants to get an array ref of lines +# see if caller wants lines + + if( wantarray || $opts->{'array_ref'} ) { -# this split doesn't work since it tries to use variable length lookbehind -# the m// line works. -# return [ split( m|(?<=$sep)|, ${$buf_ref} ) ] if $args{'array_ref'} ; - return [ length(${$buf_ref}) ? ${$buf_ref} =~ /(.*?$sep|.+)/sg : () ] - if $args{'array_ref'} ; + my @parts = split m/($sep)/, ${$buf_ref}, -1; -# caller wants a list of lines (normal list context) + my @lines ; -# same problem with this split as before. -# return split( m|(?<=$sep)|, ${$buf_ref} ) if wantarray ; - return length(${$buf_ref}) ? ${$buf_ref} =~ /(.*?$sep|.+)/sg : () - if wantarray ; + while( @parts > 2 ) { + + my( $line, $sep ) = splice( @parts, 0, 2 ) ; + push @lines, "$line$sep" ; + } + + push @lines, shift @parts if @parts && length $parts[0] ; + + return \@lines if $opts->{'array_ref'} ; + return @lines ; + } # caller wants a scalar ref to the slurped text - return $buf_ref if $args{'scalar_ref'} ; + return $buf_ref if $opts->{'scalar_ref'} ; # caller wants a scalar with the slurped text (normal scalar context) @@ -273,27 +277,130 @@ ERR # caller passed in an i/o buffer by reference (normal void context) return ; + + +# # caller wants to get an array ref of lines + +# # this split doesn't work since it tries to use variable length lookbehind +# # the m// line works. +# # return [ split( m|(?<=$sep)|, ${$buf_ref} ) ] if $opts->{'array_ref'} ; +# return [ length(${$buf_ref}) ? ${$buf_ref} =~ /(.*?$sep|.+)/sg : () ] +# if $opts->{'array_ref'} ; + +# # caller wants a list of lines (normal list context) + +# # same problem with this split as before. +# # return split( m|(?<=$sep)|, ${$buf_ref} ) if wantarray ; +# return length(${$buf_ref}) ? ${$buf_ref} =~ /(.*?$sep|.+)/sg : () +# if wantarray ; + +# # caller wants a scalar ref to the slurped text + +# return $buf_ref if $opts->{'scalar_ref'} ; + +# # caller wants a scalar with the slurped text (normal scalar context) + +# return ${$buf_ref} if defined wantarray ; + +# # caller passed in an i/o buffer by reference (normal void context) + +# return ; } + +# errors in this sub are returned as scalar refs +# a normal IO/GLOB handle is an empty return +# an overloaded object returns its stringified as a scalarfilename + +sub _check_ref { + + my( $handle ) = @_ ; + +# check if we are reading from a handle (GLOB or IO object) + + if ( eval { $handle->isa( 'GLOB' ) || $handle->isa( 'IO' ) } ) { + +# we have a handle. deal with seeking to it if it is DATA + + my $err = _seek_data_handle( $handle ) ; + +# return the error string if any + + return \$err if $err ; + +# we have good handle + return ; + } + + eval { require overload } ; + +# return an error if we can't load the overload pragma +# or if the object isn't overloaded + + return \"Bad handle '$handle' is not a GLOB or IO object or overloaded" + if $@ || !overload::Overloaded( $handle ) ; + +# must be overloaded so return its stringified value + + return "$handle" ; +} + +sub _seek_data_handle { + + my( $handle ) = @_ ; + +# DEEP DARK MAGIC. this checks the UNTAINT IO flag of a +# glob/handle. only the DATA handle is untainted (since it is from +# trusted data in the source file). this allows us to test if this is +# the DATA handle and then to do a sysseek to make sure it gets +# slurped correctly. on some systems, the buffered i/o pointer is not +# left at the same place as the fd pointer. this sysseek makes them +# the same so slurping with sysread will work. + + eval{ require B } ; + + if ( $@ ) { + + return <IO->IoFLAGS & 16 ) { + +# set the seek position to the current tell. + + unless( sysseek( $handle, tell( $handle ), SEEK_SET ) ) { + return "read_file '$handle' - sysseek: $!" ; + } + } + +# seek was successful, return no error string + + return ; +} + + sub write_file { my $file_name = shift ; # get the optional argument hash ref from @_ or an empty hash ref. - my $args = ( ref $_[0] eq 'HASH' ) ? shift : {} ; + my $opts = ( ref $_[0] eq 'HASH' ) ? shift : {} ; my( $buf_ref, $write_fh, $no_truncate, $orig_file_name, $data_is_ref ) ; # get the buffer ref - it depends on how the data is passed into write_file # after this if/else $buf_ref will have a scalar ref to the data. - if ( ref $args->{'buf_ref'} eq 'SCALAR' ) { + if ( ref $opts->{'buf_ref'} eq 'SCALAR' ) { -# a scalar ref passed in %args has the data +# a scalar ref passed in %opts has the data # note that the data was passed by ref - $buf_ref = $args->{'buf_ref'} ; + $buf_ref = $opts->{'buf_ref'} ; $data_is_ref = 1 ; } elsif ( ref $_[0] eq 'SCALAR' ) { @@ -317,20 +424,44 @@ sub write_file { ${$buf_ref} = join '', @_ ; } -# see if we were passed a open handle to spew to. +# deal with ref for a file name if ( ref $file_name ) { -# we have a handle. make sure we don't call truncate on it. + my $ref_result = _check_ref( $file_name ) ; + + if ( ref $ref_result ) { - $write_fh = $file_name ; - $no_truncate = 1 ; +# we got an error, deal with it + + @_ = ( $opts, $ref_result ) ; + goto &_error ; + } + + if ( $ref_result ) { + +# we got an overloaded object and the result is the stringified value +# use it as the file name + + $file_name = $ref_result ; + } + else { + +# we now have a proper handle ref. +# make sure we don't call truncate on it. + + $write_fh = $file_name ; + $no_truncate = 1 ; + } } - else { + +# see if we have a path we need to open + + unless( $write_fh ) { # spew to regular file. - if ( $args->{'atomic'} ) { + if ( $opts->{'atomic'} ) { # in atomic mode, we spew to a temp file so make one and save the original # file name. @@ -341,10 +472,10 @@ sub write_file { # set the mode for the sysopen my $mode = O_WRONLY | O_CREAT ; - $mode |= O_APPEND if $args->{'append'} ; - $mode |= O_EXCL if $args->{'no_clobber'} ; + $mode |= O_APPEND if $opts->{'append'} ; + $mode |= O_EXCL if $opts->{'no_clobber'} ; - my $perms = $args->{perms} ; + my $perms = $opts->{perms} ; $perms = 0666 unless defined $perms ; #printf "WR: BINARY %x MODE %x\n", O_BINARY, $mode ; @@ -353,23 +484,24 @@ sub write_file { $write_fh = gensym ; unless ( sysopen( $write_fh, $file_name, $mode, $perms ) ) { - @_ = ( $args, "write_file '$file_name' - sysopen: $!"); + + @_ = ( $opts, "write_file '$file_name' - sysopen: $!"); goto &_error ; } } - if ( my $binmode = $args->{'binmode'} ) { + if ( my $binmode = $opts->{'binmode'} ) { binmode( $write_fh, $binmode ) ; } - sysseek( $write_fh, 0, SEEK_END ) if $args->{'append'} ; + sysseek( $write_fh, 0, SEEK_END ) if $opts->{'append'} ; #print 'WR before data ', unpack( 'H*', ${$buf_ref}), "\n" ; # fix up newline to write cr/lf if this is a windows text file - if ( $is_win32 && !$args->{'binmode'} ) { + if ( $is_win32 && !$opts->{'binmode'} ) { # copy the write data if it was passed by ref so we don't clobber the # caller's data @@ -396,7 +528,7 @@ sub write_file { unless ( defined $write_cnt ) { # the write failed - @_ = ( $args, "write_file '$file_name' - syswrite: $!"); + @_ = ( $opts, "write_file '$file_name' - syswrite: $!"); goto &_error ; } @@ -417,10 +549,9 @@ sub write_file { # handle the atomic mode - move the temp file to the original filename. - if ( $args->{'atomic'} && !rename( $file_name, $orig_file_name ) ) { + if ( $opts->{'atomic'} && !rename( $file_name, $orig_file_name ) ) { - - @_ = ( $args, "write_file '$file_name' - rename: $!" ) ; + @_ = ( $opts, "write_file '$file_name' - rename: $!" ) ; goto &_error ; } @@ -438,17 +569,17 @@ sub write_file { sub append_file { -# get the optional args hash ref - my $args = $_[1] ; - if ( ref $args eq 'HASH' ) { +# get the optional opts hash ref + my $opts = $_[1] ; + if ( ref $opts eq 'HASH' ) { -# we were passed an args ref so just mark the append mode +# we were passed an opts ref so just mark the append mode - $args->{append} = 1 ; + $opts->{append} = 1 ; } else { -# no args hash so insert one with the append mode +# no opts hash so insert one with the append mode splice( @_, 1, 0, { append => 1 } ) ; } @@ -461,9 +592,70 @@ sub append_file { # basic wrapper around opendir/readdir +# prepend data to the beginning of a file + +sub prepend_file { + + my $file_name = shift ; + +#print "FILE $file_name\n" ; + + my $opts = ( ref $_[0] eq 'HASH' ) ? shift : {} ; + +# delete unsupported options + + my @bad_opts = + grep $_ ne 'err_mode' && $_ ne 'binmode', keys %{$opts} ; + + delete @{$opts}{@bad_opts} ; + + my $prepend_data = shift ; + $prepend_data = '' unless defined $prepend_data ; + $prepend_data = ${$prepend_data} if ref $prepend_data eq 'SCALAR' ; + +#print "PRE [$prepend_data]\n" ; + + +###### set croak as error_mode +###### wrap in eval + + my $err_mode = delete $opts->{err_mode} ; + $opts->{ err_mode } = 'croak' ; + $opts->{ scalar_ref } = 1 ; + + my $existing_data ; + eval { $existing_data = read_file( $file_name, $opts ) } ; + + if ( $@ ) { + + @_ = ( { err_mode => $err_mode }, + "prepend_file '$file_name' - read_file: $!" ) ; + goto &_error ; + } + +#print "EXIST [$$existing_data]\n" ; + + $opts->{ atomic } = 1 ; + + my $write_result = eval { + write_file( $file_name, $opts, + $prepend_data, $$existing_data ) ; + } ; + + if ( $@ ) { + + @_ = ( { err_mode => $err_mode }, + "prepend_file '$file_name' - write_file: $!" ) ; + goto &_error ; + } + + return $write_result ; +} + sub read_dir { - my ($dir, %args ) = @_; + my $dir = shift ; + my $opts = ( ref $_[0] eq 'HASH' ) ? shift : { @_ } ; # this handle will be destroyed upon return @@ -473,14 +665,14 @@ sub read_dir { unless ( opendir( DIRH, $dir ) ) { - @_ = ( \%args, "read_dir '$dir' - opendir: $!" ) ; + @_ = ( $opts, "read_dir '$dir' - opendir: $!" ) ; goto &_error ; } my @dir_entries = readdir(DIRH) ; @dir_entries = grep( $_ ne "." && $_ ne "..", @dir_entries ) - unless $args{'keep_dot_dot'} ; + unless $opts->{'keep_dot_dot'} ; return @dir_entries if wantarray ; return \@dir_entries ; @@ -502,11 +694,11 @@ my %err_func = ( sub _error { - my( $args, $err_msg ) = @_ ; + my( $opts, $err_msg ) = @_ ; # get the error function to use - my $func = $err_func{ $args->{'err_mode'} || 'croak' } ; + my $func = $err_func{ $opts->{'err_mode'} || 'croak' } ; # if we didn't find it in our error function hash, they must have set # it to quiet and we don't do anything. @@ -528,21 +720,37 @@ __END__ =head1 NAME -File::Slurp - Efficient Reading/Writing of Complete Files +File::Slurp - Simple and Efficient Reading/Writing of Complete Files =head1 SYNOPSIS use File::Slurp; +# read in a whole file into a scalar + my $text = read_file( 'filename' ) ; + +# read in a whole file into an array of lines + my @lines = read_file( 'filename' ) ; +# write out a whole file from a scalar + + write_file( 'filename', $text ) ; + +# write out a whole file from an array of lines + write_file( 'filename', @lines ) ; - use File::Slurp qw( slurp ) ; +# Here is a simple and fast way to load and save a simple config file +# made of key=value lines. + + my %conf = read_file( $file_name ) =~ /^(\w+)=(\.*)$/mg ; + write_file( $file_name, {atomic => 1}, map "$_=$conf{$_}\n", keys %conf ; - my $text = slurp( 'filename' ) ; +# read in a whole directory of file names (skipping . and ..) + my @files = read_dir( '/path/to/dir' ) ; =head1 DESCRIPTION @@ -552,32 +760,49 @@ flexible ways to pass in or get the file contents and to be very efficient. There is also a sub to read in all the files in a directory other than C<.> and C<..> -These slurp/spew subs work for files, pipes and -sockets, and stdio, pseudo-files, and DATA. +These slurp/spew subs work for files, pipes and sockets, stdio, +pseudo-files, and the DATA handle. Read more about why slurping files is +a good thing in the file 'slurp_article.pod' in the extras/ directory. + +If you are interested in how fast these calls work, check out the +slurp_bench.pl program in the extras/ directory. It compares many +different forms of slurping. You can select the I/O direction, context +and file sizes. Use the --help option to see how to run it. =head2 B This sub reads in an entire file and returns its contents to the -caller. In list context it will return a list of lines (using the +caller. In scalar context it returns the entire file as a single +scalar. In list context it will return a list of lines (using the current value of $/ as the separator including support for paragraph -mode when it is set to ''). In scalar context it returns the entire -file as a single scalar. +mode when it is set to ''). my $text = read_file( 'filename' ) ; + my $bin = read_file( 'filename' { binmode => ':raw' } ) ; my @lines = read_file( 'filename' ) ; + my $lines = read_file( 'filename', array_ref => 1 ) ; -The first argument to C is the filename and the rest of the -arguments are key/value pairs which are optional and which modify the -behavior of the call. Other than binmode the options all control how -the slurped file is returned to the caller. +The first argument is the file to slurp in. If the next argument is a +hash reference, then it is used as the options. Otherwise the rest of +the argument list are is used as key/value options. -If the first argument is a file handle reference or I/O object (if ref -is true), then that handle is slurped in. This mode is supported so -you slurp handles such as C, C. See the test handle.t -for an example that does C and child process spews data +If the file argument is a handle (if it is a ref and is an IO or GLOB +object), then that handle is slurped in. This mode is supported so you +slurp handles such as C and C. See the test handle.t for +an example that does C and the child process spews data to the parant which slurps it in. All of the options that control how the data is returned to the caller still work in this case. +If the first argument is an overloaded object then its stringified value +is used for the filename and that file is opened. This is a new feature +in 9999.14. See the stringify.t test for an example. + +By default C returns an undef in scalar contex or a single +undef in list context if it encounters an error. Those are both +impossible to get with a clean read_file call which means you can check +the return value and always know if you had an error. You can change how +errors are handled with the C option. + NOTE: as of version 9999.06, read_file works correctly on the C handle. It used to need a sysseek workaround but that is now handled when needed by the module itself. @@ -586,12 +811,13 @@ You can optionally request that C is exported to your code. This is an alias for read_file and is meant to be forward compatible with Perl 6 (which will have slurp() built-in). -The options are: +The options for C are: =head3 binmode -If you set the binmode option, then the option will be passed to a -binmode call on the opened filehandle. +If you set the binmode option, then its value is passed to a call to +binmode on the opened handle. You can use this to set the file to be +read in binary mode, utf8, etc. See perldoc -f binmode for more. my $bin_data = read_file( $bin_file, binmode => ':raw' ) ; my $utf_text = read_file( $bin_file, binmode => ':utf8' ) ; @@ -615,15 +841,6 @@ to return. my $text_ref = read_file( $bin_file, scalar_ref => 1 ) ; -=head3 perms - -The perms option sets the permissions of newly-created files. This value -is modified by your process's umask and defaults to 0666 (same as -sysopen). - -NOTE: this option is new as of File::Slurp version 9999.14; - - =head3 buf_ref You can use this option to pass in a scalar reference and the slurped @@ -631,13 +848,12 @@ file contents will be stored in the scalar. This can be used in conjunction with any of the other options. This saves an extra copy of the slurped file and can lower ram usage vs returning the file. - my $text_ref = read_file( $bin_file, buf_ref => \$buffer, - array_ref => 1 ) ; - my @lines = read_file( $bin_file, buf_ref => \$buffer ) ; + read_file( $bin_file, buf_ref => \$buffer ) ; =head3 blk_size -You can use this option to set the block size used when slurping from an already open handle (like \*STDIN). It defaults to 1MB. +You can use this option to set the block size used when slurping from +an already open handle (like \*STDIN). It defaults to 1MB. my $text_ref = read_file( $bin_file, blk_size => 10_000_000, array_ref => 1 ) ; @@ -645,9 +861,9 @@ You can use this option to set the block size used when slurping from an already =head3 err_mode You can use this option to control how read_file behaves when an error -occurs. This option defaults to 'croak'. You can set it to 'carp' or -to 'quiet to have no error handling. This code wants to carp and then -read abother file if it fails. +occurs. This option defaults to 'croak'. You can set it to 'carp' or to +'quiet to have no special error handling. This code wants to carp and +then read another file if it fails. my $text_ref = read_file( $file, err_mode => 'carp' ) ; unless ( $text_ref ) { @@ -670,14 +886,14 @@ modify the behavior of C. The rest of the argument list is the data to be written to the file. write_file( 'filename', {append => 1 }, @data ) ; - write_file( 'filename', {binmode => ':raw' }, $buffer ) ; - -As a shortcut if the first data argument is a scalar or array -reference, it is used as the only data to be written to the file. Any -following arguments in @_ are ignored. This is a faster way to pass in -the output to be written to the file and is equivilent to the -C option. These following pairs are equivilent but the pass -by reference call will be faster in most cases (especially with larger + write_file( 'filename', {binmode => ':raw'}, $buffer ) ; + +As a shortcut if the first data argument is a scalar or array reference, +it is used as the only data to be written to the file. Any following +arguments in @_ are ignored. This is a faster way to pass in the output +to be written to the file and is equivalent to the C option of +C. These following pairs are equivalent but the pass by +reference call will be faster in most cases (especially with larger files). write_file( 'filename', \$buffer ) ; @@ -686,35 +902,46 @@ files). write_file( 'filename', \@lines ) ; write_file( 'filename', @lines ) ; -If the first argument is a file handle reference or I/O object (if ref -is true), then that handle is slurped in. This mode is supported so -you spew to handles such as \*STDOUT. See the test handle.t for an -example that does C and child process spews data to the -parant which slurps it in. All of the options that control how the -data is passes into C still work in this case. +If the first argument is a handle (if it is a ref and is an IO or GLOB +object), then that handle is written to. This mode is supported so you +spew to handles such as \*STDOUT. See the test handle.t for an example +that does C and child process spews data to the parent +which slurps it in. All of the options that control how the data are +passed into C still work in this case. + +If the first argument is an overloaded object then its stringified value +is used for the filename and that file is opened. This is new feature +in 9999.14. See the stringify.t test for an example. -C returns 1 upon successfully writing the file or undef if -it encountered an error. +By default C returns 1 upon successfully writing the file or +undef if it encountered an error. You can change how errors are handled +with the C option. The options are: =head3 binmode -If you set the binmode option, then the file will be written in binary -mode. +If you set the binmode option, then its value is passed to a call to +binmode on the opened handle. You can use this to set the file to be +read in binary mode, utf8, etc. See perldoc -f binmode for more. write_file( $bin_file, {binmode => ':raw'}, @data ) ; + write_file( $bin_file, {binmode => ':utf8'}, $utf_text ) ; + +=head3 perms -NOTE: this actually sets the O_BINARY mode flag for sysopen. It -probably should call binmode and pass its argument to support other -file modes. +The perms option sets the permissions of newly-created files. This value +is modified by your process's umask and defaults to 0666 (same as +sysopen). + +NOTE: this option is new as of File::Slurp version 9999.14; =head3 buf_ref You can use this option to pass in a scalar reference which has the data to be written. If this is set then any data arguments (including the scalar reference shortcut) in @_ will be ignored. These are -equivilent: +equivalent: write_file( $bin_file, { buf_ref => \$buffer } ) ; write_file( $bin_file, \$buffer ) ; @@ -737,8 +964,8 @@ the current file. Internally this sets the sysopen mode flag O_APPEND. write_file( $file, {append => 1}, @data ) ; -C croaks if it cannot open the file. It returns true if it -succeeded in writing out the file and undef if there was an error. + You +can import append_file and it does the same thing. =head3 no_clobber @@ -772,11 +999,38 @@ write_file for its API and behavior. This sub will write its data to the end of the file. It is a wrapper around write_file and it has the same API so see that for the full -documentation. These calls are equivilent: +documentation. These calls are equivalent: append_file( $file, @data ) ; write_file( $file, {append => 1}, @data ) ; + +=head2 prepend_file + +This sub writes data to the beginning of a file. The previously existing +data is written after that so the effect is prepending data in front of +a file. It is a counterpart to the append_file sub in this module. It +works by first using C to slurp in the file and then calling +C with the new data and the existing file data. + +The first argument to C is the filename. The next argument +is an optional hash reference and it contains key/values that can modify +the behavior of C. The rest of the argument list is the +data to be written to the file and that is passed to C as is +(see that for allowed data). + +Only the C and C options are supported. The +C call has the C option set so you will always have +a consistant file. See above for more about those options. + +C is not exported by default, you need to import it +explicitly. + + use File::Slurp qw( prepend_file ) ; + prepend_file( $file, $header ) ; + prepend_file( $file, \@lines ) ; + prepend_file( $file, { binmode => 'raw:'}, $bin_data ) ; + =head2 read_dir This sub reads all the file names from directory and returns them to @@ -784,12 +1038,20 @@ the caller but C<.> and C<..> are removed by default. my @files = read_dir( '/path/to/dir' ) ; -It croaks if it cannot open the directory. +The first argument is the path to the directory to read. If the next +argument is a hash reference, then it is used as the options. +Otherwise the rest of the argument list are is used as key/value +options. -In a list context C returns a list of the entries in the +In list context C returns a list of the entries in the directory. In a scalar context it returns an array reference which has the entries. +=head3 err_mode + +If the C option is set, it selects how errors are handled (see +C in C or C). + =head3 keep_dot_dot If this boolean option is set, C<.> and C<..> are not removed from the @@ -817,6 +1079,6 @@ that requires B.pm which didn't get into core until 5.005. =head1 AUTHOR -Uri Guttman, Euri@stemsystems.comE +Uri Guttman, Euri AT stemsystems DOT comE =cut