u 0.5.0 → 1.0.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +7 -0
- data/build/ext/u/data/attributes.rb +39 -0
- data/build/ext/u/data/bidi-mirroring.rb +27 -0
- data/build/ext/u/data/canonical-combining-class.rb +15 -0
- data/build/ext/u/data/case-folding.rb +39 -0
- data/build/ext/u/data/cased.rb +19 -0
- data/build/ext/u/data/compose.rb +304 -0
- data/build/ext/u/data/constants.rb +31 -0
- data/build/ext/u/data/decompose.rb +85 -0
- data/build/ext/u/data/general-category.rb +61 -0
- data/build/ext/u/data/grapheme-word-break.rb +15 -0
- data/build/ext/u/data/marshalled.rb +5 -0
- data/build/ext/u/data/script.rb +91 -0
- data/build/ext/u/data/soft-dotted.rb +17 -0
- data/build/ext/u/data/title-table.rb +30 -0
- data/build/ext/u/data/wide.rb +17 -0
- data/build/lib/u/build.rb +8 -0
- data/build/lib/u/build/data.rb +16 -0
- data/build/lib/u/build/data/bidimirroring.rb +26 -0
- data/build/lib/u/build/data/break.rb +14 -0
- data/build/lib/u/build/data/casefolding.rb +77 -0
- data/build/lib/u/build/data/compositionexclusions.rb +14 -0
- data/build/lib/u/build/data/derivedeastasianwidth.rb +15 -0
- data/build/lib/u/build/data/file.rb +88 -0
- data/build/lib/u/build/data/linebreak.rb +14 -0
- data/build/lib/u/build/data/proplist.rb +18 -0
- data/build/lib/u/build/data/scripts.rb +22 -0
- data/build/lib/u/build/data/specialcasing.rb +106 -0
- data/build/lib/u/build/data/unicode.rb +41 -0
- data/build/lib/u/build/data/unicode/entry.rb +27 -0
- data/build/lib/u/build/data/unicode/entry/decomposition.rb +29 -0
- data/build/lib/u/build/data/unicode/points.rb +32 -0
- data/build/lib/u/build/header.rb +11 -0
- data/build/lib/u/build/header/table.rb +19 -0
- data/build/lib/u/build/header/table/row.rb +64 -0
- data/build/lib/u/build/header/tables.rb +6 -0
- data/build/lib/u/build/header/tables/intervals.rb +50 -0
- data/build/lib/u/build/header/tables/split.rb +20 -0
- data/build/lib/u/build/header/tables/split/data.rb +29 -0
- data/build/lib/u/build/header/tables/split/part1.rb +28 -0
- data/build/lib/u/build/header/tables/split/part2.rb +13 -0
- data/build/lib/u/build/header/tables/split/row.rb +34 -0
- data/build/lib/u/build/header/tables/split/rows.rb +22 -0
- data/build/test/unit/break.rb +45 -0
- data/build/test/unit/case.rb +178 -0
- data/build/test/unit/foldcase.rb +44 -0
- data/build/test/unit/normalize.rb +81 -0
- data/ext/u/attributes.c +62 -0
- data/ext/u/attributes.h +5 -0
- data/ext/u/case.h +41 -0
- data/ext/u/data/attributes.h +3070 -0
- data/ext/u/data/bidi-mirroring.h +373 -0
- data/ext/u/data/canonical-combining-class.h +2157 -0
- data/ext/u/data/case-folding.h +171 -0
- data/ext/u/data/cased.h +42 -0
- data/ext/u/data/compose.h +1714 -0
- data/ext/u/data/constants.h +17 -0
- data/ext/u/data/decompose.h +9356 -0
- data/ext/u/data/general-category.h +28959 -0
- data/ext/u/data/grapheme-break.h +13201 -0
- data/ext/u/data/line-break.h +26501 -0
- data/ext/u/data/normalization-quick-check.h +3002 -0
- data/ext/u/data/script.h +2928 -0
- data/ext/u/data/soft-dotted.h +55 -0
- data/ext/u/data/title-table.h +41 -0
- data/ext/u/data/types.h +11117 -0
- data/ext/u/data/wide-cjk.h +197 -0
- data/ext/u/data/wide.h +59 -0
- data/ext/u/data/word-break.h +10001 -0
- data/ext/u/depend +281 -0
- data/ext/u/extconf.rb +158 -0
- data/ext/u/output.h +51 -0
- data/ext/{encoding/character/utf-8 → u}/private.c +11 -15
- data/ext/u/private.h +58 -0
- data/ext/u/rb_includes.h +10 -0
- data/ext/u/rb_private.c +98 -0
- data/ext/u/rb_private.h +67 -0
- data/ext/u/rb_u.c +251 -0
- data/ext/u/rb_u_buffer.c +443 -0
- data/ext/u/rb_u_buffer.h +24 -0
- data/ext/u/rb_u_re.c +43 -0
- data/ext/u/rb_u_re.h +15 -0
- data/ext/u/rb_u_string.c +478 -0
- data/ext/u/rb_u_string.h +173 -0
- data/ext/u/rb_u_string_alnum.c +10 -0
- data/ext/u/rb_u_string_alpha.c +10 -0
- data/ext/u/rb_u_string_aref.c +142 -0
- data/ext/u/rb_u_string_ascii_only.c +13 -0
- data/ext/u/rb_u_string_assigned.c +10 -0
- data/ext/u/rb_u_string_b.c +18 -0
- data/ext/u/rb_u_string_bytesize.c +10 -0
- data/ext/u/rb_u_string_byteslice.c +103 -0
- data/ext/u/rb_u_string_canonical_combining_class.c +33 -0
- data/ext/u/rb_u_string_case_ignorable.c +25 -0
- data/ext/u/rb_u_string_casecmp.c +61 -0
- data/ext/u/rb_u_string_cased.c +17 -0
- data/ext/u/rb_u_string_chomp.c +107 -0
- data/ext/u/rb_u_string_chop.c +33 -0
- data/ext/u/rb_u_string_chr.c +9 -0
- data/ext/u/rb_u_string_cntrl.c +10 -0
- data/ext/u/rb_u_string_collate.c +46 -0
- data/ext/u/rb_u_string_collation_key.c +18 -0
- data/ext/u/rb_u_string_count.c +38 -0
- data/ext/u/rb_u_string_defined.c +10 -0
- data/ext/u/rb_u_string_delete.c +62 -0
- data/ext/u/rb_u_string_digit.c +10 -0
- data/ext/u/rb_u_string_downcase.c +13 -0
- data/ext/u/rb_u_string_dump.c +153 -0
- data/ext/u/rb_u_string_each_byte.c +46 -0
- data/ext/u/rb_u_string_each_char.c +49 -0
- data/ext/u/rb_u_string_each_codepoint.c +45 -0
- data/ext/u/rb_u_string_each_grapheme_cluster.c +36 -0
- data/ext/u/rb_u_string_each_line.c +142 -0
- data/ext/u/rb_u_string_each_word.c +34 -0
- data/ext/u/rb_u_string_empty.c +11 -0
- data/ext/u/rb_u_string_end_with.c +31 -0
- data/ext/u/rb_u_string_eql.c +30 -0
- data/ext/u/rb_u_string_equal.c +33 -0
- data/ext/u/rb_u_string_foldcase.c +12 -0
- data/ext/u/rb_u_string_folded.c +13 -0
- data/ext/u/rb_u_string_format.c +1745 -0
- data/ext/u/rb_u_string_general_category.c +109 -0
- data/ext/u/rb_u_string_getbyte.c +21 -0
- data/ext/u/rb_u_string_graph.c +21 -0
- data/ext/u/rb_u_string_grapheme_break.c +61 -0
- data/ext/u/rb_u_string_gsub.c +164 -0
- data/ext/u/rb_u_string_hash.c +10 -0
- data/ext/u/rb_u_string_hex.c +9 -0
- data/ext/u/rb_u_string_include.c +10 -0
- data/ext/u/rb_u_string_index.c +110 -0
- data/ext/u/rb_u_string_inspect.c +189 -0
- data/ext/u/rb_u_string_internal_tr.c +148 -0
- data/ext/u/rb_u_string_internal_tr.h +29 -0
- data/ext/u/rb_u_string_justify.c +169 -0
- data/ext/u/rb_u_string_length.c +10 -0
- data/ext/u/rb_u_string_line_break.c +115 -0
- data/ext/u/rb_u_string_lower.c +13 -0
- data/ext/u/rb_u_string_lstrip.c +24 -0
- data/ext/u/rb_u_string_match.c +65 -0
- data/ext/u/rb_u_string_mirror.c +16 -0
- data/ext/u/rb_u_string_newline.c +21 -0
- data/ext/u/rb_u_string_normalize.c +70 -0
- data/ext/u/rb_u_string_normalized.c +28 -0
- data/ext/u/rb_u_string_oct.c +11 -0
- data/ext/u/rb_u_string_ord.c +14 -0
- data/ext/u/rb_u_string_partition.c +80 -0
- data/ext/u/rb_u_string_plus.c +33 -0
- data/ext/u/rb_u_string_print.c +10 -0
- data/ext/u/rb_u_string_punct.c +10 -0
- data/ext/u/rb_u_string_reverse.c +13 -0
- data/ext/u/rb_u_string_rindex.c +104 -0
- data/ext/u/rb_u_string_rpartition.c +81 -0
- data/ext/u/rb_u_string_rstrip.c +29 -0
- data/ext/u/rb_u_string_scan.c +109 -0
- data/ext/u/rb_u_string_script.c +253 -0
- data/ext/u/rb_u_string_soft_dotted.c +13 -0
- data/ext/u/rb_u_string_space.c +24 -0
- data/ext/u/rb_u_string_split.c +245 -0
- data/ext/u/rb_u_string_squeeze.c +75 -0
- data/ext/u/rb_u_string_start_with.c +31 -0
- data/ext/u/rb_u_string_strip.c +36 -0
- data/ext/u/rb_u_string_sub.c +147 -0
- data/ext/u/rb_u_string_times.c +35 -0
- data/ext/u/rb_u_string_title.c +10 -0
- data/ext/u/rb_u_string_titlecase.c +13 -0
- data/ext/u/rb_u_string_to_i.c +45 -0
- data/ext/u/rb_u_string_to_inum.c +364 -0
- data/ext/u/rb_u_string_to_inum.h +1 -0
- data/ext/u/rb_u_string_to_str.c +17 -0
- data/ext/u/rb_u_string_to_sym.c +12 -0
- data/ext/u/rb_u_string_tr.c +290 -0
- data/ext/u/rb_u_string_upcase.c +12 -0
- data/ext/u/rb_u_string_upper.c +13 -0
- data/ext/u/rb_u_string_valid.c +10 -0
- data/ext/u/rb_u_string_valid_encoding.c +12 -0
- data/ext/u/rb_u_string_wide.c +21 -0
- data/ext/u/rb_u_string_wide_cjk.c +21 -0
- data/ext/u/rb_u_string_width.c +19 -0
- data/ext/u/rb_u_string_word_break.c +63 -0
- data/ext/u/rb_u_string_xdigit.c +22 -0
- data/ext/u/rb_u_string_zero_width.c +16 -0
- data/ext/u/titled.c +55 -0
- data/ext/u/titled.h +1 -0
- data/ext/u/u.c +23 -0
- data/ext/u/u.h +458 -0
- data/ext/u/u_char_canonical_combining_class.c +31 -0
- data/ext/u/u_char_digit_value.c +21 -0
- data/ext/u/u_char_downcase.c +27 -0
- data/ext/u/u_char_general_category.c +31 -0
- data/ext/u/u_char_grapheme_break.c +28 -0
- data/ext/u/u_char_isalnum.c +24 -0
- data/ext/u/u_char_isalpha.c +21 -0
- data/ext/u/u_char_isassigned.c +16 -0
- data/ext/u/u_char_iscased.c +22 -0
- data/ext/u/u_char_iscaseignorable.c +29 -0
- data/ext/u/u_char_iscntrl.c +17 -0
- data/ext/u/u_char_isdefined.c +15 -0
- data/ext/u/u_char_isdigit.c +16 -0
- data/ext/u/u_char_isgraph.c +22 -0
- data/ext/u/u_char_islower.c +16 -0
- data/ext/u/u_char_isnewline.c +24 -0
- data/ext/u/u_char_isprint.c +21 -0
- data/ext/u/u_char_ispunct.c +27 -0
- data/ext/u/u_char_issoftdotted.c +18 -0
- data/ext/u/u_char_isspace.c +28 -0
- data/ext/u/u_char_isupper.c +16 -0
- data/ext/u/u_char_isvalid.c +18 -0
- data/ext/u/u_char_iswide.c +18 -0
- data/ext/u/u_char_iswide_cjk.c +22 -0
- data/ext/u/u_char_isxdigit.c +27 -0
- data/ext/u/u_char_iszerowidth.c +29 -0
- data/ext/u/u_char_line_break.c +29 -0
- data/ext/u/u_char_mirror.c +16 -0
- data/ext/u/u_char_normalized.c +23 -0
- data/ext/u/u_char_script.c +41 -0
- data/ext/u/u_char_to_u.c +48 -0
- data/ext/u/u_char_upcase.c +24 -0
- data/ext/u/u_char_width.c +12 -0
- data/ext/u/u_char_word_break.c +28 -0
- data/ext/u/u_char_xdigit_value.c +31 -0
- data/ext/u/u_collate.c +83 -0
- data/ext/u/u_collation_key.c +132 -0
- data/ext/u/u_decode.c +156 -0
- data/ext/u/u_downcase.c +201 -0
- data/ext/u/u_foldcase.c +68 -0
- data/ext/u/u_grapheme_clusters.c +57 -0
- data/ext/u/u_has_prefix.c +27 -0
- data/ext/u/u_index.c +93 -0
- data/ext/u/u_is_ascii_only.c +33 -0
- data/ext/u/u_locale.c +40 -0
- data/ext/u/u_locale.h +14 -0
- data/ext/u/u_mirror.c +20 -0
- data/ext/u/u_n_bytes.c +16 -0
- data/ext/u/u_n_chars.c +43 -0
- data/ext/u/u_normalize.c +232 -0
- data/ext/u/u_normalized.c +28 -0
- data/ext/u/u_offset_to_pointer.c +62 -0
- data/ext/u/u_pointer_to_offset.c +23 -0
- data/ext/u/u_recode.c +73 -0
- data/ext/u/u_reverse.c +21 -0
- data/ext/u/u_rindex.c +132 -0
- data/ext/u/u_titlecase.c +68 -0
- data/ext/u/u_upcase.c +89 -0
- data/ext/u/u_width.c +35 -0
- data/ext/u/u_words.c +82 -0
- data/ext/u/yield.h +27 -0
- data/lib/u-1.0.rb +20 -0
- data/lib/u-1.0/buffer.rb +10 -0
- data/lib/u-1.0/string.rb +9 -0
- data/lib/u-1.0/version.rb +287 -0
- data/test/unit/case.rb +2080 -0
- data/test/unit/foldcase.rb +1136 -0
- data/test/unit/graphemebreak.rb +407 -0
- data/test/unit/normalize.rb +367545 -0
- data/test/unit/u-1.0.rb +10 -0
- data/test/unit/u-1.0/buffer.rb +52 -0
- data/test/unit/u-1.0/string.rb +1439 -0
- data/test/unit/{u.rb → u-1.0/version.rb} +0 -1
- data/test/unit/wordbreak.rb +1083 -0
- metadata +603 -148
- data/README +0 -38
- data/Rakefile +0 -64
- data/ext/encoding/character/utf-8/break.c +0 -25
- data/ext/encoding/character/utf-8/data/break.h +0 -22931
- data/ext/encoding/character/utf-8/data/character-tables.h +0 -14358
- data/ext/encoding/character/utf-8/data/compose.h +0 -1607
- data/ext/encoding/character/utf-8/data/decompose.h +0 -10926
- data/ext/encoding/character/utf-8/data/generate-unicode-data.rb +0 -1070
- data/ext/encoding/character/utf-8/decompose.c +0 -444
- data/ext/encoding/character/utf-8/depend +0 -65
- data/ext/encoding/character/utf-8/extconf.rb +0 -67
- data/ext/encoding/character/utf-8/private.h +0 -51
- data/ext/encoding/character/utf-8/properties.c +0 -1056
- data/ext/encoding/character/utf-8/rb_includes.h +0 -19
- data/ext/encoding/character/utf-8/rb_methods.h +0 -49
- data/ext/encoding/character/utf-8/rb_private.h +0 -52
- data/ext/encoding/character/utf-8/rb_utf_aref.c +0 -111
- data/ext/encoding/character/utf-8/rb_utf_aset.c +0 -105
- data/ext/encoding/character/utf-8/rb_utf_casecmp.c +0 -24
- data/ext/encoding/character/utf-8/rb_utf_chomp.c +0 -114
- data/ext/encoding/character/utf-8/rb_utf_chop.c +0 -44
- data/ext/encoding/character/utf-8/rb_utf_collate.c +0 -13
- data/ext/encoding/character/utf-8/rb_utf_count.c +0 -30
- data/ext/encoding/character/utf-8/rb_utf_delete.c +0 -60
- data/ext/encoding/character/utf-8/rb_utf_downcase.c +0 -13
- data/ext/encoding/character/utf-8/rb_utf_each_char.c +0 -27
- data/ext/encoding/character/utf-8/rb_utf_foldcase.c +0 -13
- data/ext/encoding/character/utf-8/rb_utf_hex.c +0 -14
- data/ext/encoding/character/utf-8/rb_utf_index.c +0 -50
- data/ext/encoding/character/utf-8/rb_utf_insert.c +0 -48
- data/ext/encoding/character/utf-8/rb_utf_internal_bignum.c +0 -332
- data/ext/encoding/character/utf-8/rb_utf_internal_bignum.h +0 -12
- data/ext/encoding/character/utf-8/rb_utf_internal_tr.c +0 -142
- data/ext/encoding/character/utf-8/rb_utf_internal_tr.h +0 -41
- data/ext/encoding/character/utf-8/rb_utf_justify.c +0 -96
- data/ext/encoding/character/utf-8/rb_utf_length.c +0 -14
- data/ext/encoding/character/utf-8/rb_utf_lstrip.c +0 -41
- data/ext/encoding/character/utf-8/rb_utf_normalize.c +0 -51
- data/ext/encoding/character/utf-8/rb_utf_oct.c +0 -14
- data/ext/encoding/character/utf-8/rb_utf_reverse.c +0 -13
- data/ext/encoding/character/utf-8/rb_utf_rindex.c +0 -88
- data/ext/encoding/character/utf-8/rb_utf_rstrip.c +0 -51
- data/ext/encoding/character/utf-8/rb_utf_squeeze.c +0 -70
- data/ext/encoding/character/utf-8/rb_utf_strip.c +0 -27
- data/ext/encoding/character/utf-8/rb_utf_to_i.c +0 -25
- data/ext/encoding/character/utf-8/rb_utf_tr.c +0 -250
- data/ext/encoding/character/utf-8/rb_utf_upcase.c +0 -13
- data/ext/encoding/character/utf-8/tables.h +0 -38
- data/ext/encoding/character/utf-8/unicode.c +0 -319
- data/ext/encoding/character/utf-8/unicode.h +0 -216
- data/ext/encoding/character/utf-8/utf.c +0 -1334
- data/lib/encoding/character/utf-8.rb +0 -201
- data/lib/u.rb +0 -16
- data/lib/u/string.rb +0 -185
- data/lib/u/version.rb +0 -5
- data/test/unit/u/string.rb +0 -91
@@ -0,0 +1,64 @@
|
|
1
|
+
# -*- coding: utf-8 -*-
|
2
|
+
|
3
|
+
class U::Build::Header::Table::Row
|
4
|
+
def initialize(*cells)
|
5
|
+
@cells = cells
|
6
|
+
end
|
7
|
+
|
8
|
+
def <<(cell)
|
9
|
+
@cells << cell
|
10
|
+
self
|
11
|
+
end
|
12
|
+
|
13
|
+
def to_s
|
14
|
+
if @cells.reduce(0){ |i, cell| i + cell.length + 2 } > multi_limit
|
15
|
+
lines = [Line.new]
|
16
|
+
@cells.each_with_index do |cell, i|
|
17
|
+
lines << Line.new if lines.last.length + cell.length + 2 > multi_limit - 3
|
18
|
+
lines.last << cell
|
19
|
+
end
|
20
|
+
multi_format % lines.join(multi_joiner)
|
21
|
+
else
|
22
|
+
single_format % @cells.join(', ')
|
23
|
+
end
|
24
|
+
end
|
25
|
+
|
26
|
+
private
|
27
|
+
|
28
|
+
def multi_limit
|
29
|
+
65
|
30
|
+
end
|
31
|
+
|
32
|
+
def multi_format
|
33
|
+
"\t{\n\t\t%s\n\t}"
|
34
|
+
end
|
35
|
+
|
36
|
+
def multi_joiner
|
37
|
+
",\n\t\t"
|
38
|
+
end
|
39
|
+
|
40
|
+
def single_format
|
41
|
+
"\t{ %s }"
|
42
|
+
end
|
43
|
+
|
44
|
+
class Line
|
45
|
+
def initialize
|
46
|
+
@cells = []
|
47
|
+
@length = 0
|
48
|
+
end
|
49
|
+
|
50
|
+
def <<(cell)
|
51
|
+
@cells << cell
|
52
|
+
@length += cell.length
|
53
|
+
self
|
54
|
+
end
|
55
|
+
|
56
|
+
def length
|
57
|
+
@length + (@cells.length - 1) * 2
|
58
|
+
end
|
59
|
+
|
60
|
+
def to_s
|
61
|
+
@cells.join(', ')
|
62
|
+
end
|
63
|
+
end
|
64
|
+
end
|
@@ -0,0 +1,50 @@
|
|
1
|
+
# -*- coding: utf-8 -*-
|
2
|
+
|
3
|
+
class U::Build::Header::Tables::Intervals < U::Build::Header::Table
|
4
|
+
def initialize(points, name)
|
5
|
+
super 'static const struct uint32_t_interval %s[]' % name
|
6
|
+
return if points.empty?
|
7
|
+
sorted = points.sort
|
8
|
+
first = sorted[0]
|
9
|
+
last = first - 1
|
10
|
+
sorted.each do |point|
|
11
|
+
if point == last + 1
|
12
|
+
last += 1
|
13
|
+
else
|
14
|
+
row first, last
|
15
|
+
first = point
|
16
|
+
last = first
|
17
|
+
end
|
18
|
+
end
|
19
|
+
row first, last
|
20
|
+
end
|
21
|
+
|
22
|
+
def to_s
|
23
|
+
'%s%s' % [<<EOH, super]
|
24
|
+
struct uint32_t_interval {
|
25
|
+
uint32_t first;
|
26
|
+
uint32_t last;
|
27
|
+
};
|
28
|
+
|
29
|
+
static int
|
30
|
+
u_char_interval_compare(const void *key, const void *element)
|
31
|
+
{
|
32
|
+
uint32_t c = *(uint32_t *)key;
|
33
|
+
struct uint32_t_interval *interval = (struct uint32_t_interval *)element;
|
34
|
+
|
35
|
+
if (c < interval->first)
|
36
|
+
return -1;
|
37
|
+
else if (c > interval->last)
|
38
|
+
return +1;
|
39
|
+
else
|
40
|
+
return 0;
|
41
|
+
}
|
42
|
+
EOH
|
43
|
+
end
|
44
|
+
|
45
|
+
private
|
46
|
+
|
47
|
+
def row(first, last)
|
48
|
+
self << U::Build::Header::Table::Row.new('%#06x, %#06x' % [first, last])
|
49
|
+
end
|
50
|
+
end
|
@@ -0,0 +1,20 @@
|
|
1
|
+
# -*- coding: utf-8 -*-
|
2
|
+
|
3
|
+
class U::Build::Header::Tables::Split
|
4
|
+
require 'u/build/header/tables/split/row'
|
5
|
+
require 'u/build/header/tables/split/rows'
|
6
|
+
require 'u/build/header/tables/split/data'
|
7
|
+
require 'u/build/header/tables/split/part1'
|
8
|
+
require 'u/build/header/tables/split/part2'
|
9
|
+
|
10
|
+
def initialize(data, type, name)
|
11
|
+
rows = Rows.new(0, data.last){ |c| yield(c) }
|
12
|
+
@data = Data.new('%s %s_data' % [type, name], rows)
|
13
|
+
@part1 = Part1.new('%s_table_part1' % name, 0, data.last_char_part1_i, rows, 0)
|
14
|
+
@part2 = Part2.new('%s_table_part2' % name, data.last, rows, @part1)
|
15
|
+
end
|
16
|
+
|
17
|
+
def to_s
|
18
|
+
"%s\n%s\n%s" % [@data, @part1, @part2]
|
19
|
+
end
|
20
|
+
end
|
@@ -0,0 +1,29 @@
|
|
1
|
+
# -*- coding: utf-8 -*-
|
2
|
+
|
3
|
+
class U::Build::Header::Tables::Split::Data < U::Build::Header::Table
|
4
|
+
def initialize(declaration, rows)
|
5
|
+
super 'static const %s[][256]' % declaration
|
6
|
+
rows.reject{ |row| row.homogenous? }.each_with_index do |row, index|
|
7
|
+
table_row = Row.new(row.start / 256, index)
|
8
|
+
row.each do |cell|
|
9
|
+
table_row << cell
|
10
|
+
end
|
11
|
+
self << table_row
|
12
|
+
end
|
13
|
+
end
|
14
|
+
|
15
|
+
private
|
16
|
+
|
17
|
+
class Row < U::Build::Header::Table::Row
|
18
|
+
def initialize(page, index)
|
19
|
+
super()
|
20
|
+
@format = "\t{ /* page %d, index %d */\n\t\t%%s\n\t}" % [page, index]
|
21
|
+
end
|
22
|
+
|
23
|
+
private
|
24
|
+
|
25
|
+
def multi_format
|
26
|
+
@format
|
27
|
+
end
|
28
|
+
end
|
29
|
+
end
|
@@ -0,0 +1,28 @@
|
|
1
|
+
# -*- coding: utf-8 -*-
|
2
|
+
|
3
|
+
class U::Build::Header::Tables::Split::Part1 < U::Build::Header::Table
|
4
|
+
class << self
|
5
|
+
def last_page
|
6
|
+
'UNICODE_LAST_PAGE_PART1'
|
7
|
+
end
|
8
|
+
end
|
9
|
+
|
10
|
+
def initialize(name, first, last, rows, set = 0)
|
11
|
+
super "/* U+%04X through U+%04X */\nstatic const int16_t %s[%s + 1]" % [first, last, name, self.class.last_page]
|
12
|
+
# TODO: Check if we can use each or something, instead, or if we can use
|
13
|
+
# an array for Rows.
|
14
|
+
j = set
|
15
|
+
first.step(last, 256) do |i|
|
16
|
+
row = rows[i / 256]
|
17
|
+
if row.homogenous?
|
18
|
+
self << "\t%s + UNICODE_MAX_TABLE_INDEX" % row[0]
|
19
|
+
else
|
20
|
+
self << "\t%d /* page %d */" % [j, row.start / 256]
|
21
|
+
j += 1
|
22
|
+
end
|
23
|
+
end
|
24
|
+
@set = j
|
25
|
+
end
|
26
|
+
|
27
|
+
attr_reader :set
|
28
|
+
end
|
@@ -0,0 +1,13 @@
|
|
1
|
+
# -*- coding: utf-8 -*-
|
2
|
+
|
3
|
+
class U::Build::Header::Tables::Split::Part2 < U::Build::Header::Tables::Split::Part1
|
4
|
+
class << self
|
5
|
+
def last_page
|
6
|
+
'UNICODE_LAST_PAGE_PART2'
|
7
|
+
end
|
8
|
+
end
|
9
|
+
|
10
|
+
def initialize(name, last, rows, part1)
|
11
|
+
super name, 0xe0000, last, rows, part1.set
|
12
|
+
end
|
13
|
+
end
|
@@ -0,0 +1,34 @@
|
|
1
|
+
# -*- coding: utf-8 -*-
|
2
|
+
|
3
|
+
class U::Build::Header::Tables::Split::Row
|
4
|
+
include Enumerable
|
5
|
+
|
6
|
+
def initialize(start)
|
7
|
+
@start = start
|
8
|
+
@cells = []
|
9
|
+
# TODO: Perhaps don’t cache this if this turns out to be too memory
|
10
|
+
# consuming.
|
11
|
+
@homogenous = true
|
12
|
+
0.upto(255) do |i|
|
13
|
+
@cells[i] = yield(start + i)
|
14
|
+
@homogenous = false if @cells[i] != @cells[0]
|
15
|
+
end
|
16
|
+
end
|
17
|
+
|
18
|
+
def each
|
19
|
+
@cells.each do |cell|
|
20
|
+
yield cell
|
21
|
+
end
|
22
|
+
self
|
23
|
+
end
|
24
|
+
|
25
|
+
def [](index)
|
26
|
+
@cells[index]
|
27
|
+
end
|
28
|
+
|
29
|
+
def homogenous?
|
30
|
+
@homogenous
|
31
|
+
end
|
32
|
+
|
33
|
+
attr_reader :start
|
34
|
+
end
|
@@ -0,0 +1,22 @@
|
|
1
|
+
# -*- coding: utf-8 -*-
|
2
|
+
|
3
|
+
class U::Build::Header::Tables::Split::Rows
|
4
|
+
include Enumerable
|
5
|
+
|
6
|
+
def initialize(first, last)
|
7
|
+
@rows = []
|
8
|
+
first.step(last, 256) do |i|
|
9
|
+
@rows[i / 256] = U::Build::Header::Tables::Split::Row.new(i){ |c| yield(c) }
|
10
|
+
end
|
11
|
+
end
|
12
|
+
|
13
|
+
def each
|
14
|
+
@rows.each do |row|
|
15
|
+
yield row
|
16
|
+
end
|
17
|
+
end
|
18
|
+
|
19
|
+
def [](index)
|
20
|
+
@rows[index]
|
21
|
+
end
|
22
|
+
end
|
@@ -0,0 +1,45 @@
|
|
1
|
+
# -*- coding: utf-8 -*-
|
2
|
+
|
3
|
+
class Break
|
4
|
+
def initialize(path, method, io = $stdout)
|
5
|
+
io.puts '# -*- coding: utf-8 -*-',
|
6
|
+
'# Automatically generated, so don’t edit!',
|
7
|
+
'',
|
8
|
+
'Expectations do'
|
9
|
+
Lines.new(path).each do |splits|
|
10
|
+
io.printf " expect [%s] do %s.%s.to_a end\n",
|
11
|
+
splits.map{ |e| uify(e) }.join(', '),
|
12
|
+
uify(splits.join(' ')),
|
13
|
+
method
|
14
|
+
end
|
15
|
+
io.puts 'end'
|
16
|
+
end
|
17
|
+
|
18
|
+
private
|
19
|
+
|
20
|
+
def uify(chars)
|
21
|
+
"[%s].pack('U*').u" % chars.split(' ').map{ |e| '0x%04x' % (e == 'D800' ? 0x0001 : e.to_i(16)) }.join(', ')
|
22
|
+
end
|
23
|
+
|
24
|
+
class Lines
|
25
|
+
include Enumerable
|
26
|
+
|
27
|
+
def initialize(path)
|
28
|
+
@path = path
|
29
|
+
end
|
30
|
+
|
31
|
+
def each
|
32
|
+
File.open(@path, 'r') do |file|
|
33
|
+
file.each_line.with_index do |line, index|
|
34
|
+
next if line =~ /\A(?:#|\s*\Z)/
|
35
|
+
yield line.gsub(/\s*\u{d7}\s*/, ' ').
|
36
|
+
sub(/\A\s*\u{f7}\s*/, '').
|
37
|
+
sub(/\s*#.*\Z/, '').
|
38
|
+
split(/\s*\u{f7}\s*/)
|
39
|
+
end
|
40
|
+
end
|
41
|
+
end
|
42
|
+
end
|
43
|
+
end
|
44
|
+
|
45
|
+
Break.new ARGV[0], ARGV[1]
|
@@ -0,0 +1,178 @@
|
|
1
|
+
# -*- coding: utf-8 -*-
|
2
|
+
|
3
|
+
module Utfify
|
4
|
+
class << self
|
5
|
+
def utfify(codepoints)
|
6
|
+
return '' if codepoints.empty?
|
7
|
+
codepoints.split(/\s+/).map{ |cp| cp.hex }.pack('U*')
|
8
|
+
end
|
9
|
+
end
|
10
|
+
end
|
11
|
+
|
12
|
+
class SpecialCasing
|
13
|
+
def initialize(path)
|
14
|
+
@entries = []
|
15
|
+
|
16
|
+
Lines.new(path).each do |fields|
|
17
|
+
@entries[fields[Code].hex] =
|
18
|
+
Entry.new(Utfify.utfify(fields[Upper]),
|
19
|
+
Utfify.utfify(fields[Lower]),
|
20
|
+
Utfify.utfify(fields[Title]),
|
21
|
+
fields[Condition])
|
22
|
+
end
|
23
|
+
end
|
24
|
+
|
25
|
+
def include?(code)
|
26
|
+
@entries[code]
|
27
|
+
end
|
28
|
+
|
29
|
+
def [](code)
|
30
|
+
@entries[code]
|
31
|
+
end
|
32
|
+
|
33
|
+
class Entry
|
34
|
+
def initialize(upper, lower, title, condition)
|
35
|
+
@upper, @lower, @title, @condition = upper, lower, title, condition
|
36
|
+
end
|
37
|
+
|
38
|
+
attr_reader :upper, :lower, :title, :condition
|
39
|
+
end
|
40
|
+
|
41
|
+
private
|
42
|
+
|
43
|
+
Code, Lower, Title, Upper, Condition = (0..4).to_a
|
44
|
+
|
45
|
+
class Lines
|
46
|
+
include Enumerable
|
47
|
+
|
48
|
+
def initialize(path)
|
49
|
+
@path = path
|
50
|
+
end
|
51
|
+
|
52
|
+
def each
|
53
|
+
File.open(@path, 'rb') do |file|
|
54
|
+
file.each_line.with_index do |line, index|
|
55
|
+
next if line =~ /\A(?:#|\s*\Z)/
|
56
|
+
fields = line.chomp.sub(/\s*;\s*#.*\Z/, '').split(/\s*;\s*/)
|
57
|
+
raise RuntimeError,
|
58
|
+
'%s:%d: wrong number of fields: %d instead of 4..5' %
|
59
|
+
[@path, index + 1, fields.size] unless fields.size.between? 4, 5
|
60
|
+
yield fields
|
61
|
+
end
|
62
|
+
end
|
63
|
+
end
|
64
|
+
end
|
65
|
+
end
|
66
|
+
|
67
|
+
class UnicodeData
|
68
|
+
include Enumerable
|
69
|
+
|
70
|
+
def initialize(path)
|
71
|
+
@entries = []
|
72
|
+
|
73
|
+
Lines.new(path).each do |code, fields|
|
74
|
+
@entries << Entry.new(code, fields[Category], fields[Upper], fields[Lower])
|
75
|
+
end
|
76
|
+
end
|
77
|
+
|
78
|
+
def each
|
79
|
+
@entries.each do |entry|
|
80
|
+
yield entry
|
81
|
+
end
|
82
|
+
end
|
83
|
+
|
84
|
+
class Entry
|
85
|
+
def initialize(code, category, upper, lower)
|
86
|
+
@code, @category, @upper, @lower = code, category, upper, lower
|
87
|
+
end
|
88
|
+
|
89
|
+
attr_reader :code, :category, :upper, :lower
|
90
|
+
end
|
91
|
+
|
92
|
+
private
|
93
|
+
|
94
|
+
Code, Name, Category, _, _, _, _, _, _, _, _, _, Upper, Lower, Title = (0..14).to_a
|
95
|
+
|
96
|
+
class Lines
|
97
|
+
include Enumerable
|
98
|
+
|
99
|
+
def initialize(path)
|
100
|
+
@path = path
|
101
|
+
end
|
102
|
+
|
103
|
+
def each
|
104
|
+
File.open(@path, 'rb') do |file|
|
105
|
+
previous = -1
|
106
|
+
file.each_line.with_index do |line, index|
|
107
|
+
next if line =~ /\A(?:#|\s*\Z)/
|
108
|
+
fields = line.split(';')
|
109
|
+
raise RuntimeError,
|
110
|
+
'%s:%d: wrong number of fields: %d instead of 15' %
|
111
|
+
[@path, index + 1, fields.size] unless fields.size == 15
|
112
|
+
code = fields[Code].hex
|
113
|
+
if code > previous + 1 and fields[Name] =~ /Last>$/ and fields[Category] =~ /^L[lut]$/
|
114
|
+
previous.upto(code - 1) do |c|
|
115
|
+
yield c, fields
|
116
|
+
end
|
117
|
+
end
|
118
|
+
yield code, fields
|
119
|
+
previous = code
|
120
|
+
end
|
121
|
+
end
|
122
|
+
end
|
123
|
+
end
|
124
|
+
end
|
125
|
+
|
126
|
+
class Case
|
127
|
+
def initialize(special, unicode_data, io = $stdout)
|
128
|
+
@special, @io = special, io
|
129
|
+
@io.puts '# -*- coding: utf-8 -*-',
|
130
|
+
'# Automatically generated, so don’t edit!',
|
131
|
+
'',
|
132
|
+
'Expectations do'
|
133
|
+
unicode_data.each do |entry|
|
134
|
+
generate entry
|
135
|
+
end
|
136
|
+
@io.puts 'end'
|
137
|
+
end
|
138
|
+
|
139
|
+
private
|
140
|
+
|
141
|
+
def generate(entry)
|
142
|
+
case entry.category
|
143
|
+
when 'Ll'
|
144
|
+
upcase entry
|
145
|
+
when 'Lu'
|
146
|
+
downcase entry
|
147
|
+
when 'Lt'
|
148
|
+
upcase entry
|
149
|
+
downcase entry
|
150
|
+
end
|
151
|
+
end
|
152
|
+
|
153
|
+
def upcase(entry)
|
154
|
+
if @special.include? entry.code
|
155
|
+
generate1 @special[entry.code].upper, u(entry), :upcase if not @special[entry.code].condition
|
156
|
+
elsif not entry.upper.empty?
|
157
|
+
generate1 Utfify.utfify(entry.upper), u(entry), :upcase
|
158
|
+
end
|
159
|
+
end
|
160
|
+
|
161
|
+
def downcase(entry)
|
162
|
+
if @special.include? entry.code
|
163
|
+
generate1 @special[entry.code].lower, u(entry), :downcase if not @special[entry.code].condition
|
164
|
+
elsif not entry.lower.empty?
|
165
|
+
generate1 Utfify.utfify(entry.lower), u(entry), :downcase
|
166
|
+
end
|
167
|
+
end
|
168
|
+
|
169
|
+
def generate1(expected, u, method)
|
170
|
+
@io.printf " expect '%s'.u do %s.%s end\n", expected, u, method
|
171
|
+
end
|
172
|
+
|
173
|
+
def u(entry)
|
174
|
+
"'%s'.u" % [entry.code].pack('U*')
|
175
|
+
end
|
176
|
+
end
|
177
|
+
|
178
|
+
Case.new SpecialCasing.new(ARGV[0]), UnicodeData.new(ARGV[1])
|