From 73ba1144c3e6a9895d09a9abbd00d9c8b649f07b Mon Sep 17 00:00:00 2001 From: Karl Williamson Date: Sat, 8 Oct 2011 13:25:56 -0600 Subject: [PATCH] mktables: More detail on ignored files This improves the wording on files that are delivered by Unicode and aren't used by mktables; and adds the documentation files that previously weren't listed. This is in preparation for perluniprops listing these. --- lib/unicore/mktables | 27 +++++++++++++++------------ 1 file changed, 15 insertions(+), 12 deletions(-) diff --git a/lib/unicore/mktables b/lib/unicore/mktables index d9f083f..1e7796f 100644 --- a/lib/unicore/mktables +++ b/lib/unicore/mktables @@ -1053,18 +1053,21 @@ my %default_mapping = ( # Below are files that Unicode furnishes, but this program ignores, and why my %ignored_files = ( - 'CJKRadicals.txt' => 'Unihan data', - 'Index.txt' => 'An index, not actual data', - 'NamedSqProv.txt' => 'Not officially part of the Unicode standard; Append it to NamedSequences.txt if you want to process the contents.', - 'NamesList.txt' => 'Just adds commentary', - 'NormalizationCorrections.txt' => 'Data is already in other files.', - 'Props.txt' => 'Adds nothing to PropList.txt; only in very early releases', - 'ReadMe.txt' => 'Just comments', - 'README.TXT' => 'Just comments', - 'StandardizedVariants.txt' => 'Only for glyph changes, not a Unicode character property. Does not fit into current scheme where one code point is mapped', - 'EmojiSources.txt' => 'Not of general utility: for Japanese legacy cell-phone applications', - 'IndicMatraCategory.txt' => 'Provisional', - 'IndicSyllabicCategory.txt' => 'Provisional', + 'CJKRadicals.txt' => 'Maps the kRSUnicode property values to corresponding code points', + 'Index.txt' => 'Alphabetical index of Unicode characters', + 'NamedSqProv.txt' => 'Named sequences proposed for inclusion in a later version of the Unicode Standard; if you need them now, you can append this file to F and recompile perl', + 'NamesList.txt' => 'Annotated list of characters', + 'NormalizationCorrections.txt' => 'Documentation of corrections already incorporated into the Unicode data base', + 'Props.txt' => 'Only in very early releases; is a subset of F (which is used instead)', + 'ReadMe.txt' => 'Documentation', + 'StandardizedVariants.txt' => 'Certain glyph variations for character display are standardized. This lists the non-Unihan ones; the Unihan ones are also not used by Perl, and are in a separate Unicode data base L', + 'EmojiSources.txt' => 'Maps certain Unicode code points to their legacy Japanese cell-phone values', + 'IndicMatraCategory.txt' => 'Provisional; for the analysis and processing of Indic scripts', + 'IndicSyllabicCategory.txt' => 'Provisional; for the analysis and processing of Indic scripts', + 'auxiliary/WordBreakTest.html' => 'Documentation of validation tests', + 'auxiliary/SentenceBreakTest.html' => 'Documentation of validation tests', + 'auxiliary/GraphemeBreakTest.html' => 'Documentation of validation tests', + 'auxiliary/LineBreakTest.html' => 'Documentation of validation tests', ); ### End of externally interesting definitions, except for @input_file_objects -- 2.7.4