1 | #!/usr/bin/perl -w
|
---|
2 |
|
---|
3 | ###########################################################################
|
---|
4 | #
|
---|
5 | # gti-process-google-spreadsheet.pl
|
---|
6 | #
|
---|
7 | # A component of the Greenstone digital library software
|
---|
8 | # from the New Zealand Digital Library Project at the
|
---|
9 | # University of Waikato, New Zealand.
|
---|
10 | #
|
---|
11 | # Copyright (C) 2005 New Zealand Digital Library Project
|
---|
12 | #
|
---|
13 | # This program is free software; you can redistribute it and/or modify
|
---|
14 | # it under the terms of the GNU General Public License as published by
|
---|
15 | # the Free Software Foundation; either version 2 of the License, or
|
---|
16 | # (at your option) any later version.
|
---|
17 | #
|
---|
18 | # This program is distributed in the hope that it will be useful,
|
---|
19 | # but WITHOUT ANY WARRANTY; without even the implied warranty of
|
---|
20 | # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
---|
21 | # GNU General Public License for more details.
|
---|
22 | #
|
---|
23 | # You should have received a copy of the GNU General Public License
|
---|
24 | # along with this program; if not, write to the Free Software
|
---|
25 | # Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
|
---|
26 | #
|
---|
27 | ###########################################################################
|
---|
28 |
|
---|
29 |
|
---|
30 | # This script takes a spreadsheet of 3 columns: the key, English, <translated language>
|
---|
31 | # and returns XML that Greenstone likes.
|
---|
32 | # Use of this file and where it fits in the processing of translation files is
|
---|
33 | # explained in gti-xml-to-spreadsheet.xsl (and gti-tmx-to-spreadsheet.xsl).
|
---|
34 |
|
---|
35 |
|
---|
36 | use strict;
|
---|
37 |
|
---|
38 |
|
---|
39 | sub main
|
---|
40 | {
|
---|
41 | # Required parameter: the path of the spreadsheet file saved in UTF-16 Excel text format
|
---|
42 | my $utf16_excel_txt_file_path = shift(@_);
|
---|
43 | if (!defined($utf16_excel_txt_file_path)) {
|
---|
44 | die "Usage: gti-process-spreadsheet.pl <txt-file-path>\n";
|
---|
45 | }
|
---|
46 |
|
---|
47 | # Ensure the UTF-16 Excel text file exists
|
---|
48 | if (!-f $utf16_excel_txt_file_path) {
|
---|
49 | die "Error: UTF-16 Excel text file $utf16_excel_txt_file_path does not exist.\n";
|
---|
50 | }
|
---|
51 |
|
---|
52 | # Convert the Excel text file from UTF-16 to UTF-8
|
---|
53 | my $excel_txt_file_path = $utf16_excel_txt_file_path . "-utf8";
|
---|
54 | if (!-f $excel_txt_file_path) {
|
---|
55 | # Only bother if the file doesn't already exist
|
---|
56 | `iconv -f UTF-16 -t UTF-8 $utf16_excel_txt_file_path -o $excel_txt_file_path`;
|
---|
57 | }
|
---|
58 |
|
---|
59 | # Read the (UTF-8) Excel Unicode text file data
|
---|
60 | open(EXCEL_TXT_FILE, $excel_txt_file_path);
|
---|
61 | my @excel_txt_file_lines = <EXCEL_TXT_FILE>;
|
---|
62 | close(EXCEL_TXT_FILE);
|
---|
63 |
|
---|
64 | print STDERR "Number of chunks: " . scalar(@excel_txt_file_lines) . "\n";
|
---|
65 | shift(@excel_txt_file_lines); # Ignore the header row (Key Source Target)
|
---|
66 |
|
---|
67 | # Process each submitted chunk, row by row
|
---|
68 | foreach my $chunk (@excel_txt_file_lines) {
|
---|
69 |
|
---|
70 | # Remove any nasty carriage returns (especially at the end of each row/line)
|
---|
71 | $chunk =~ s/\r//;
|
---|
72 | # Just in case the newline at the end of each line is not /r but /n
|
---|
73 | $chunk =~ s/\n//;
|
---|
74 |
|
---|
75 | #print STDOUT "**** chunk: $chunk\n";
|
---|
76 |
|
---|
77 | # each Excel row's 3 fields are delimited by tabs not commas
|
---|
78 | my ($key, $source, $target) = split(/\t/, $chunk);
|
---|
79 |
|
---|
80 | # Remove the quotes around multiline chunks
|
---|
81 | if ($source =~ /^\"/ && $source =~ /\"$/) {
|
---|
82 | $source =~ s/^\"//;
|
---|
83 | $source =~ s/\"$//;
|
---|
84 | }
|
---|
85 | if ($target =~ /^\"/ && $target =~ /\"$/) {
|
---|
86 | $target =~ s/^\"//;
|
---|
87 | $target =~ s/\"$//;
|
---|
88 | }
|
---|
89 |
|
---|
90 | # Legacy: trim any leading blank space
|
---|
91 | $source =~ s/^ //g;
|
---|
92 | $target =~ s/^ //g;
|
---|
93 |
|
---|
94 | # Remove Excel's doubled-up quotes
|
---|
95 | $source =~ s/\"\"/\"/g;
|
---|
96 | $target =~ s/\"\"/\"/g;
|
---|
97 |
|
---|
98 | # replace html entity for newline with actual newline
|
---|
99 | # No longer need to replace commas (,) and double-quotes (") here, because
|
---|
100 | # gti-xml-to-spreadsheet.xslt doesn't insert entities for those anymore.
|
---|
101 | # http://www.w3.org/MarkUp/html3/latin1.html
|
---|
102 | $source =~ s/ /\n/g;
|
---|
103 | $target =~ s/ /\n/g;
|
---|
104 |
|
---|
105 | #print STDOUT "***** key: $key\n";
|
---|
106 | #print STDOUT "***** \tsource: $source\n";
|
---|
107 | #print STDOUT "***** \ttarget: $target\n\n";
|
---|
108 |
|
---|
109 | print "<SourceFileText key=\"source::" . $key . "\">\n" . $source . "\n</SourceFileText>\n";
|
---|
110 | print "<TargetFileText key=\"target::" . $key . "\">\n" . $target . "\n</TargetFileText>\n";
|
---|
111 |
|
---|
112 | }
|
---|
113 | }
|
---|
114 |
|
---|
115 |
|
---|
116 | &main(@ARGV);
|
---|