File: xlscat

package info (click to toggle)
libspreadsheet-read-perl 0.41-1
  • links: PTS, VCS
  • area: main
  • in suites: wheezy
  • size: 568 kB
  • sloc: perl: 2,605; lisp: 293; makefile: 9; xml: 1
file content (312 lines) | stat: -rwxr-xr-x 9,573 bytes parent folder | download | duplicates (2)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
#!/pro/bin/perl

# xls2cat: show XLS/SXC file as Text
#	  (m)'09 [13-05-2009] Copyright H.M.Brand 2005-2010

use strict;
use warnings;

our $VERSION = "1.9";

sub usage
{
    my $err = shift and select STDERR;
    print
	"usage: xlscat [-s <sep>] [-L] [-n] [-A] [-u] [ Selection ] file.xls\n",
	"              [-c | -m]                 [-u] [ Selection ] file.xls\n",
	"               -i                            [ -S sheets ] file.xls\n",
	"    Generic options:\n",
	"       -v[#]       Set verbose level (xlscat)\n",
	"       -d[#]       Set debug   level (Spreadsheet::Read)\n",
	"       -u          Use unformatted values\n",
	"       --noclip    Do not strip empty sheets and\n",
	"                   trailing empty rows and columns\n",
	"	-e <enc>    Set encoding for input and output\n",
	"	-b <enc>    Set encoding for input\n",
	"	-a <enc>    Set encoding for output\n",
	"    Input CSV:\n",
	"       --in-sep=c  Set input sep_char for CSV\n",
	"    Input XLS:\n",
	"       --dtfmt=fmt Specify the default date format to replace 'm-d-yy'\n",
	"                   the default replacement is 'yyyy-mm-dd'\n",
	"    Output Text (default):\n",
	"       -s <sep>    Use separator <sep>. Default '|', \\n allowed\n",
	"       -L          Line up the columns\n",
	"       -n          Number lines (prefix with column number)\n",
	"       -A          Show field attributes in ANSI escapes\n",
	"    Output Index only:\n",
	"       -i          Show sheet names and size only\n",
	"    Output CSV:\n",
	"       -c          Output CSV, separator = ','\n",
	"       -m          Output CSV, separator = ';'\n",
	"    Selection:\n",
	"       -S <sheets> Only print sheets <sheets>. 'all' is a valid set\n",
	"                   Default only prints the first sheet\n",
	"       -R <rows>   Only print rows    <rows>. Default is 'all'\n",
	"       -C <cols>   Only print columns <cols>. Default is 'all'\n",
	"       -F <flds>   Only fields <flds> e.g. -FA3,B16\n";
    @_ and print join "\n", @_, "";
    exit $err;
    } # usage

use Getopt::Long qw(:config bundling nopermute noignorecase);
my $opt_c;		# Generate CSV
my $opt_s;		# Text separator
my $opt_S;		# Sheets to print
my $opt_R;		# Rows to print
my $opt_C;		# Columns to print
my $dtfmt;		# Default date-format for Excel
my $opt_F = "";		# Fields to print
my $opt_i = 0;		# Index
my $opt_L = 0;		# Auto-size/align columns
my $opt_n = 0;		# Prefix lines with column number
my $opt_u = 0;		# Show unformatted values
my $opt_v = 0;		# Verbosity for xlscat
my $opt_d = 0;		# Debug level for Spreadsheet::Read
my $opt_A = 0;		# Show field colors in ANSI escapes
my $clip  = 1;
my $enc_i;		# Input  encoding
my $enc_o;		# Output encoding
my $sep;		# Input field sep for CSV
GetOptions (
    "help|?"		=> sub { usage (0); },

    # Input CSV
    "c|csv"		=> sub { $opt_c = "," },
    "m|ms"		=> sub { $opt_c = ";" },
    "insepchar".
     "|in-sep-char=s"	=> \$sep,

    # Input XLS
    "dtfmt".
     "|date-format=s"	=> \$dtfmt,

    # Output
    "i|index"		=> \$opt_i,
    "s|separator".
     "|outsepchar".
     "|out-sep-char=s"	=> \$opt_s,
    "S|sheets=s"	=> \$opt_S,
    "R|rows=s"		=> \$opt_R,
    "C|columns=s"	=> \$opt_C,
    "F|fields=s"	=> \$opt_F,
    "L|fit|align"	=> \$opt_L,
    "n|number"		=> \$opt_n,
    "A|ansi"		=> \$opt_A,
    "u|unformatted"	=> \$opt_u,
    "v|verbose:1"	=> \$opt_v,
    "d|debug:1"		=> \$opt_d,
    "noclip"		=> sub { $clip = 0 },

    # Encoding
    "e|encoding=s"	=> sub { $enc_i = $enc_o = $_[1] },
    "b|encoding-in=s"	=> \$enc_i,
    "a|encoding-out=s"	=> \$enc_o,
    ) or usage 1, "GetOpt: $@";

$opt_i && $opt_L and usage 1, "Options i and L are mutually exclusive";
$opt_i && $opt_s and usage 1, "Options i and s are mutually exclusive";
$opt_i && $opt_c and usage 1, "Options i and c are mutually exclusive";
$opt_i && $opt_u and usage 1, "Options i and u are mutually exclusive";
$opt_i && $opt_S and usage 1, "Options i and S are mutually exclusive";
$opt_i && $opt_R and usage 1, "Options i and R are mutually exclusive";
$opt_i && $opt_C and usage 1, "Options i and C are mutually exclusive";
$opt_i && $opt_F and usage 1, "Options i and F are mutually exclusive";
$opt_c && $opt_s and usage 1, "Options c and s are mutually exclusive";

defined $opt_s or $opt_s = "|"; eval "\$opt_s = qq{$opt_s}";
defined $opt_S or $opt_S = $opt_i ? "all" : "1";
$opt_i && $opt_v < 1 and $opt_v = 1;

if ($opt_c) {
    $opt_L = 0;	# Cannot align CSV
    $opt_c =~ m/^1?$/ and $opt_c = ",";
    $opt_c = Text::CSV_XS->new ({
	binary   => 1,
	sep_char => $opt_c,
	eol      => "\r\n",
	});
    }

use Data::Dumper;	# I should use Data::Peek instead
   $Data::Dumper::Sortkeys = 1;
   $Data::Dumper::Indent   = 1;

@ARGV or usage 1;
my $file = shift;
-f $file or usage 1, "the first argument is not a regular file";
-s $file or usage 1, "the file is empty";

use Encode qw( encode decode );
use Spreadsheet::Read;
if ($opt_c) {
    Spreadsheet::Read::parses ("csv") or die "No CSV module found\n";
    eval { use Text::CSV_XS };
    }

my @RDarg = (debug => $opt_d, clip => $clip);
$opt_A         and push @RDarg, "attr"  => 1;
defined $sep   and push @RDarg, "sep"   => $sep;
defined $dtfmt and push @RDarg, "dtfmt" => $dtfmt;
$opt_v > 4 and print STDERR "ReadData ($file, @RDarg);\n";
my $xls = ReadData ($file, @RDarg) or die "cannot read $file\n";
$opt_v > 7 and print STDERR Dumper ($xls);
my $sc  = $xls->[0]{sheets}	or die "No sheets in $file\n";
$opt_v > 1 and print STDERR "Opened $file with $sc sheets\n";

$opt_S eq "all" and $opt_S = "1..$sc";	# all
$opt_S =~ s/-$/-$sc/;			# 3,6-
$opt_S =~ s/-/../g;
my %print;
eval "%{\$print{sheet}} = map { \$_ => 1 } $opt_S";

my $v_fmt = $opt_C || $opt_R || $opt_F ? "" : "%6d x %6d%s";

# New style xterm (based on ANSI colors):
# 30 Black
# 31 Red
# 32 Green
# 33 Yellow
# 34 Blue
# 35 Magenta
# 36 Cyan
# 37 White
sub color_reduce
{
    my ($rgb, $base) = @_;
    defined $rgb or return "";
    my ($r, $g, $b) = map { hex >> 7 }
	($rgb =~ m/^\s*#?([\da-f]{2})([\da-f]{2})([\da-f]{2})/);
    $base + 4 * $b + 2 * $g + $r;
    } # color_reduce

sub ansi_color
{
    my ($fg, $bg, $bold, $ul) = @_;

    #print STDERR "$fg on $bg $bold $ul\n";
    my $attr = join ";", 0, grep { /\S/ }
	$bold ? 1 : "",
	$ul   ? 4 : "",
	color_reduce ($fg, 30),
	color_reduce ($bg, 40);

    "\e[${attr}m";
    } # ansi_color

	    binmode STDERR, ":utf8";
$enc_o and  binmode STDOUT, ":encoding($enc_o)";

my $name_len = 30;
if ($opt_i) {
    my $nl = 0;
    foreach my $sn (keys %{$xls->[0]{sheet}}) {
	length ($sn) > $nl and $nl = length $sn;
	}
    $nl and $name_len = $nl;
    }
my @opt_F = split m/[^A-Z\d]+/ => $opt_F;
foreach my $si (1 .. $sc) {
    my @data;
    exists $print{sheet}{$si} or next;
    $opt_v > 1 and print STDERR "Opening sheet $si ...\n";
    my $s = $xls->[$si] or next;
    $opt_v > 5 and print STDERR Dumper ($s);
    my @r = (1, $s->{maxrow});
    my @c = (1, $s->{maxcol});
    my ($sn, $nr, $nc) = ($s->{label}, $r[-1], $c[-1]);
    $opt_v and printf STDERR "%s - %02d: [ %-*s ] %3d Cols, %5d Rows\n",
	$file, $si, $name_len, $sn, $nc, $nr;
    $opt_i and next;

    if (@opt_F) {
	foreach my $fld (@opt_F) {
	    print "$fld:",$s->{$fld},"\n";
	    }
	next;
	}

    if (my $rows = $opt_R) {
	$rows eq "all" and $rows = "1..$nr";	# all
	$rows =~ s/-$/-$nr/;			# 3,6-
	$rows =~ s/-/../g;
	eval "%{\$print{row}} = map { \$_ => 1 } $rows";
	}
    if (my $cols = $opt_C) {
	$cols eq "all" and $cols = "1..$nc";	# all
	$cols =~ s/-$/-$nc/;			# 3,6-
	$cols =~ s/-/../g;
	eval "\$print{col} = [ map { \$_ - 1  } $cols ]";
	$nc = @{$print{col}};
	}
    $opt_v >= 8 and print Dumper (\%print);

    my $undef = $opt_v > 2 ? "-- undef --" : "";
    my ($h, @w) = (0, (0) x $nc); # data height, -width, and default column widths
    my @align = ("") x $nc;
    foreach my $r ($r[0] .. $r[1]) {
	exists $print{row} && !exists $print{row}{$r} and next;
	my @att;
	my @row = map {
	    my $cell = cr2cell ($_, $r);
	    my ($uval, $fval) = map {
		defined $_ ? $enc_i ? decode ($enc_i, $_) : $_ : $undef
		} $s->{cell}[$_][$r], $s->{$cell};
	    $opt_v > 2 and print STDERR "$_:$r '$uval' / '$fval'\n";
	    $opt_A and 
		push @att, [ @{$s->{attr}[$_][$r]}{qw( fgcolor bgcolor bold uline )} ];
	    defined $s->{cell}[$_][$r] ? $opt_u ? $uval : $fval : "";
	    } $c[0] .. $c[1];
	exists $print{col} and @row = @row[@{$print{col}}];
	if ($opt_L) {
	    foreach my $c (0 .. $#row) {
		my $l = length $row[$c];
		$l > $w[$c] and $w[$c] = $l;
		$row[$c] =~ m/\D/ and $align[$c] = "-";
		}
	    }
	if ($opt_c) {	# CSV
	    if ($enc_o) { $_ = encode ($enc_o, $_) for @row; }
	    $opt_c->print (*STDOUT, \@row) or die $opt_c->error_diag;
	    next;
	    }
	if ($opt_n) {
	    unshift @row, $r;
	    unshift @att, [ "#ffffff", "#000000", 0, 0 ];
	    }
	if ($opt_L) {	# Autofit / Align
	    push @data, [ [ @row ], [ @att ] ];
	    next;
	    }
	if ($opt_A) {
	    foreach my $c (0 .. $#row) {
		$row[$c] =
		    ansi_color (@{$att[$c]}).
		    $row[$c] .
		    "\e[0m";
		}
	    }
	print join ($opt_s => @row), "\n";
	} continue {
	    ++$h % 100 or printf STDERR $v_fmt, $nc, $h, "\r";
	    }
    printf STDERR $v_fmt, $nc, $h, "\n";
    $opt_L or next;
    if ($opt_n) {
	unshift @w, length $data[-1][0][0];
	unshift @align, "";
	}
    my $fmt = join ($opt_s =>
	map { my $f = "%$align[$_]$w[$_]s";
	      $opt_A ? "%s$f%s" : $f } 0 .. $#w)."\n";
    for (@data) {
	my ($row, $att) = @$_;
	my @row = $opt_A
	    ? map { (
		ansi_color (@{$att->[$_]}),
		$row->[$_],
		"\e[0m" ) } 0 .. $#$row
	    : @$row;
	printf $fmt, @row;
	}
    }