[13296] | 1 | #!/usr/bin/perl -w
|
---|
| 2 |
|
---|
| 3 | ###########################################################################
|
---|
| 4 | #
|
---|
| 5 | # gti-process-excel-xml.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 | use strict;
|
---|
| 31 |
|
---|
| 32 |
|
---|
| 33 | sub main
|
---|
| 34 | {
|
---|
| 35 | # Required parameter: the path of the spreadsheet file saved in UTF-16 Excel text format
|
---|
| 36 | my $utf16_excel_txt_file_path = shift(@_);
|
---|
| 37 | if (!defined($utf16_excel_txt_file_path)) {
|
---|
| 38 | die "Usage: gti-process-spreadsheet.pl <txt-file-path>\n";
|
---|
| 39 | }
|
---|
| 40 |
|
---|
| 41 | # Ensure the UTF-16 Excel text file exists
|
---|
| 42 | if (!-f $utf16_excel_txt_file_path) {
|
---|
| 43 | die "Error: UTF-16 Excel text file $utf16_excel_txt_file_path does not exist.\n";
|
---|
| 44 | }
|
---|
| 45 |
|
---|
| 46 | # Convert the Excel text file from UTF-16 to UTF-8
|
---|
| 47 | my $excel_txt_file_path = $utf16_excel_txt_file_path . "-utf8";
|
---|
| 48 | if (!-f $excel_txt_file_path) {
|
---|
| 49 | # Only bother if the file doesn't already exist
|
---|
| 50 | `iconv -f UTF-16 -t UTF-8 $utf16_excel_txt_file_path -o $excel_txt_file_path`;
|
---|
| 51 | }
|
---|
| 52 |
|
---|
| 53 | # Read the (UTF-8) Excel Unicode text file data
|
---|
| 54 | open(EXCEL_TXT_FILE, $excel_txt_file_path);
|
---|
| 55 | my @excel_txt_file_lines = <EXCEL_TXT_FILE>;
|
---|
| 56 | my $excel_txt_file_data = join("", @excel_txt_file_lines);
|
---|
| 57 | close(EXCEL_TXT_FILE);
|
---|
| 58 |
|
---|
| 59 | # Remove any nasty carriage returns
|
---|
| 60 | $excel_txt_file_data =~ s/\r//g;
|
---|
| 61 |
|
---|
[13318] | 62 | # Make sure the first line is where we want it, and remove all stray whitespace
|
---|
[13296] | 63 | $excel_txt_file_data =~ s/^(\n)*/\n\n/;
|
---|
[13318] | 64 | $excel_txt_file_data =~ s/\n(\s*)\n/\n\n/g;
|
---|
[13296] | 65 |
|
---|
| 66 | # Split into chunks
|
---|
| 67 | my @chunks = split(/\n\nsource::/, $excel_txt_file_data);
|
---|
| 68 | shift(@chunks); # Ignore the first (empty) chunk
|
---|
| 69 | print STDERR "Number of chunks: " . scalar(@chunks) . "\n";
|
---|
| 70 |
|
---|
| 71 | # Check we've split the chunks correctly
|
---|
| 72 | my $total_number_of_chunks = ($excel_txt_file_data =~ s/source::/source::/g);
|
---|
| 73 | if (scalar(@chunks) != $total_number_of_chunks) {
|
---|
[13318] | 74 | die "Error: Expected $total_number_of_chunks chunks but only have " . scalar(@chunks) . " from splitting";
|
---|
[13296] | 75 | }
|
---|
| 76 |
|
---|
| 77 | # Process each submitted chunk
|
---|
| 78 | foreach my $chunk (@chunks) {
|
---|
| 79 | my $source_file_chunk = (split(/\ntarget::/, $chunk))[0];
|
---|
| 80 | my $target_file_chunk = (split(/\ntarget::/, $chunk))[1];
|
---|
| 81 |
|
---|
| 82 | # Parse the chunk key and chunk text
|
---|
| 83 | $source_file_chunk =~ /^(\S+)\s+((.|\n)*)$/;
|
---|
| 84 | my $source_file_chunk_key = $1;
|
---|
[28503] | 85 | # print STDERR "******** key: |$source_file_chunk_key| ";
|
---|
[13296] | 86 | my $source_file_chunk_text = $2;
|
---|
[28503] | 87 | # print STDERR "******** text: |$source_file_chunk_text|\n";
|
---|
[13296] | 88 | $target_file_chunk =~ /^(\S+)\s+((.|\n)*)$/;
|
---|
| 89 | my $target_file_chunk_key = $1;
|
---|
| 90 | my $target_file_chunk_text = $2;
|
---|
| 91 |
|
---|
| 92 | # Remove the quotes around multiline chunks
|
---|
| 93 | if ($source_file_chunk_text =~ /^\"/ && $source_file_chunk_text =~ /\"$/) {
|
---|
[28503] | 94 | # print STDERR "******** source text: |$source_file_chunk_text| \n";
|
---|
[13296] | 95 | $source_file_chunk_text =~ s/^\"//;
|
---|
| 96 | $source_file_chunk_text =~ s/\"$//;
|
---|
| 97 | }
|
---|
| 98 | if ($target_file_chunk_text =~ /^\"/ && $target_file_chunk_text =~ /\"$/) {
|
---|
[28503] | 99 | # print STDERR "******** target text: |$target_file_chunk_text| \n";
|
---|
[13296] | 100 | $target_file_chunk_text =~ s/^\"//;
|
---|
| 101 | $target_file_chunk_text =~ s/\"$//;
|
---|
| 102 | }
|
---|
[28503] | 103 | # else {
|
---|
| 104 | # print STDERR "******** !target text: |$target_file_chunk_text| \n";
|
---|
| 105 | # }
|
---|
[13296] | 106 |
|
---|
| 107 | # Remove the blank space Excel adds at the start of each line
|
---|
| 108 | $source_file_chunk_text =~ s/\n /\n/g;
|
---|
| 109 | $target_file_chunk_text =~ s/\n /\n/g;
|
---|
| 110 |
|
---|
| 111 | # Remove Excel's doubled-up quotes
|
---|
| 112 | $source_file_chunk_text =~ s/\"\"/\"/g;
|
---|
| 113 | $target_file_chunk_text =~ s/\"\"/\"/g;
|
---|
| 114 |
|
---|
[28503] | 115 | # ensure newline html entities in the unicode txt file version of the spreadsheet are replaced with newlines
|
---|
| 116 | $source_file_chunk_text =~ s/ /\n/g;
|
---|
| 117 | $target_file_chunk_text =~ s/ /\n/g;
|
---|
| 118 |
|
---|
[13296] | 119 | print "<SourceFileText key=\"" . $source_file_chunk_key . "\">\n" . $source_file_chunk_text . "\n</SourceFileText>\n";
|
---|
| 120 | print "<TargetFileText key=\"" . $target_file_chunk_key . "\">\n" . $target_file_chunk_text . "\n</TargetFileText>\n";
|
---|
| 121 | }
|
---|
| 122 | }
|
---|
| 123 |
|
---|
| 124 |
|
---|
| 125 | &main(@ARGV);
|
---|