ucode 0.2.0 → 0.2.2
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- checksums.yaml +4 -4
- data/Gemfile +10 -2
- data/README.md +66 -20
- data/Rakefile +19 -8
- data/TODO.extract-code-chart/01-pdf-fetch-validation.md +80 -0
- data/TODO.extract-code-chart/02-block-name-resolver.md +68 -0
- data/TODO.extract-code-chart/03-codechart-namespace.md +82 -0
- data/TODO.extract-code-chart/04-codechart-extractor.md +154 -0
- data/TODO.extract-code-chart/05-provenance-and-sidecar.md +147 -0
- data/TODO.extract-code-chart/06-codechart-writer.md +134 -0
- data/TODO.extract-code-chart/07-codechart-cli.md +135 -0
- data/TODO.extract-code-chart/08-specs.md +87 -0
- data/config/unicode17_universal_glyph_set.yml +1 -1
- data/lib/ucode/audit/reference_factory.rb +1 -1
- data/lib/ucode/cli.rb +101 -0
- data/lib/ucode/code_chart/extractor.rb +120 -0
- data/lib/ucode/code_chart/provenance.rb +82 -0
- data/lib/ucode/code_chart/sidecar.rb +52 -0
- data/lib/ucode/code_chart/writer.rb +128 -0
- data/lib/ucode/code_chart.rb +39 -0
- data/lib/ucode/commands/fetch.rb +1 -1
- data/lib/ucode/commands/glyphs.rb +1 -1
- data/lib/ucode/commands/lookup.rb +1 -1
- data/lib/ucode/commands/parse.rb +1 -1
- data/lib/ucode/coordinator/indices.rb +2 -2
- data/lib/ucode/error.rb +11 -0
- data/lib/ucode/fetch/code_charts.rb +3 -4
- data/lib/ucode/fetch/http.rb +75 -7
- data/lib/ucode/glyphs/page_renderer.rb +15 -2
- data/lib/ucode/glyphs/pipeline.rb +1 -2
- data/lib/ucode/parsers/blocks.rb +34 -0
- data/lib/ucode/repo/aggregate_writer.rb +1 -1
- data/lib/ucode/repo/writers/blocks_writer.rb +13 -13
- data/lib/ucode/repo/writers/enums_writer.rb +2 -2
- data/lib/ucode/repo/writers/indexes_writer.rb +4 -4
- data/lib/ucode/repo/writers/manifest_writer.rb +4 -4
- data/lib/ucode/repo/writers/named_sequences_writer.rb +1 -1
- data/lib/ucode/repo/writers/planes_writer.rb +17 -17
- data/lib/ucode/repo/writers/relationships_writer.rb +1 -1
- data/lib/ucode/repo/writers/scripts_writer.rb +6 -6
- data/lib/ucode/repo/writers.rb +1 -1
- data/lib/ucode/version.rb +1 -1
- data/lib/ucode.rb +3 -0
- data/ucode.gemspec +6 -1
- metadata +19 -6
data/lib/ucode/parsers/blocks.rb
CHANGED
|
@@ -37,6 +37,40 @@ module Ucode
|
|
|
37
37
|
nil
|
|
38
38
|
end
|
|
39
39
|
|
|
40
|
+
# Resolves a block by its identifier (the underscored form of
|
|
41
|
+
# the block name, e.g. "Basic_Latin", "Egyptian_Hieroglyphs_Extended-B").
|
|
42
|
+
# Streams `Blocks.txt` once and short-circuits on first match —
|
|
43
|
+
# callers don't need to walk the whole ~340-block file.
|
|
44
|
+
#
|
|
45
|
+
# @param path [Pathname, String] path to a Blocks.txt
|
|
46
|
+
# @param id [String] block identifier (matches `Models::Block#id`)
|
|
47
|
+
# @return [Models::Block, nil] the block, or nil when no block
|
|
48
|
+
# has the given id
|
|
49
|
+
def find_by_id(path, id)
|
|
50
|
+
return nil if id.nil? || id.empty?
|
|
51
|
+
|
|
52
|
+
each_record(path) do |block|
|
|
53
|
+
return block if block.id == id
|
|
54
|
+
end
|
|
55
|
+
nil
|
|
56
|
+
end
|
|
57
|
+
|
|
58
|
+
# Same as {find_by_id} but raises {Ucode::UnknownBlockError} on
|
|
59
|
+
# miss. Use this in callers that can't recover from a missing
|
|
60
|
+
# block (CLI commands, extractors that need a block to proceed).
|
|
61
|
+
#
|
|
62
|
+
# @param path [Pathname, String] path to a Blocks.txt
|
|
63
|
+
# @param id [String] block identifier
|
|
64
|
+
# @return [Models::Block]
|
|
65
|
+
# @raise [Ucode::UnknownBlockError] when no block matches
|
|
66
|
+
def find_by_id!(path, id)
|
|
67
|
+
find_by_id(path, id) or
|
|
68
|
+
raise Ucode::UnknownBlockError.new(
|
|
69
|
+
"unknown Unicode block: #{id.inspect}",
|
|
70
|
+
context: { block_id: id, blocks_txt: path.to_s },
|
|
71
|
+
)
|
|
72
|
+
end
|
|
73
|
+
|
|
40
74
|
private
|
|
41
75
|
|
|
42
76
|
def build_block(range, name)
|
|
@@ -45,12 +45,12 @@ module Ucode
|
|
|
45
45
|
path = Paths.blocks_index_path(@output_root)
|
|
46
46
|
summary = @blocks.map do |block|
|
|
47
47
|
{
|
|
48
|
-
"id"
|
|
49
|
-
"name"
|
|
50
|
-
"first_cp"
|
|
51
|
-
"last_cp"
|
|
48
|
+
"id" => block.id,
|
|
49
|
+
"name" => block.name,
|
|
50
|
+
"first_cp" => block.range_first,
|
|
51
|
+
"last_cp" => block.range_last,
|
|
52
52
|
"plane_number" => block.plane_number,
|
|
53
|
-
"age"
|
|
53
|
+
"age" => @block_ages[block.id],
|
|
54
54
|
}
|
|
55
55
|
end
|
|
56
56
|
write_atomic(path, to_pretty_json(summary)) ? 1 : 0
|
|
@@ -58,16 +58,16 @@ module Ucode
|
|
|
58
58
|
|
|
59
59
|
def block_payload(block)
|
|
60
60
|
to_pretty_json(
|
|
61
|
-
"id"
|
|
62
|
-
"name"
|
|
63
|
-
"range_first"
|
|
64
|
-
"range_last"
|
|
65
|
-
"plane_number"
|
|
66
|
-
"age"
|
|
67
|
-
"codepoint_ids"
|
|
61
|
+
"id" => block.id,
|
|
62
|
+
"name" => block.name,
|
|
63
|
+
"range_first" => block.range_first,
|
|
64
|
+
"range_last" => block.range_last,
|
|
65
|
+
"plane_number" => block.plane_number,
|
|
66
|
+
"age" => @block_ages[block.id],
|
|
67
|
+
"codepoint_ids" => @block_codepoint_ids[block.id] || [],
|
|
68
68
|
)
|
|
69
69
|
end
|
|
70
70
|
end
|
|
71
71
|
end
|
|
72
72
|
end
|
|
73
|
-
end
|
|
73
|
+
end
|
|
@@ -27,7 +27,7 @@ module Ucode
|
|
|
27
27
|
def write
|
|
28
28
|
path = Pathname(@output_root).join("enums.json")
|
|
29
29
|
payload = {
|
|
30
|
-
"properties"
|
|
30
|
+
"properties" => @property_aliases.map(&:to_yaml_hash),
|
|
31
31
|
"property_values" => @property_value_aliases.map(&:to_yaml_hash),
|
|
32
32
|
}
|
|
33
33
|
write_atomic(path, to_pretty_json(payload)) ? 1 : 0
|
|
@@ -35,4 +35,4 @@ module Ucode
|
|
|
35
35
|
end
|
|
36
36
|
end
|
|
37
37
|
end
|
|
38
|
-
end
|
|
38
|
+
end
|
|
@@ -34,11 +34,11 @@ module Ucode
|
|
|
34
34
|
def write
|
|
35
35
|
count = 0
|
|
36
36
|
count += 1 if write_atomic(Paths.names_index_path(@output_root),
|
|
37
|
-
|
|
37
|
+
to_pretty_json(@names))
|
|
38
38
|
count += 1 if write_atomic(Paths.labels_index_path(@output_root),
|
|
39
|
-
|
|
39
|
+
to_pretty_json(@labels))
|
|
40
40
|
count += 1 if write_atomic(codepoint_to_block_path,
|
|
41
|
-
|
|
41
|
+
to_pretty_json(@cp_to_block))
|
|
42
42
|
count
|
|
43
43
|
end
|
|
44
44
|
|
|
@@ -50,4 +50,4 @@ module Ucode
|
|
|
50
50
|
end
|
|
51
51
|
end
|
|
52
52
|
end
|
|
53
|
-
end
|
|
53
|
+
end
|
|
@@ -45,10 +45,10 @@ module Ucode
|
|
|
45
45
|
def write
|
|
46
46
|
path = Paths.manifest_path(@output_root)
|
|
47
47
|
content = {
|
|
48
|
-
"ucd_version"
|
|
48
|
+
"ucd_version" => @ucd_version,
|
|
49
49
|
"codepoint_count" => @codepoint_count,
|
|
50
|
-
"glyph_count"
|
|
51
|
-
"schema_version"
|
|
50
|
+
"glyph_count" => @glyph_count,
|
|
51
|
+
"schema_version" => SCHEMA_VERSION,
|
|
52
52
|
}
|
|
53
53
|
ts = preserved_or_new_timestamp(path, content)
|
|
54
54
|
payload = content.merge("generated_at" => ts)
|
|
@@ -75,4 +75,4 @@ module Ucode
|
|
|
75
75
|
end
|
|
76
76
|
end
|
|
77
77
|
end
|
|
78
|
-
end
|
|
78
|
+
end
|
|
@@ -16,16 +16,16 @@ module Ucode
|
|
|
16
16
|
# Static metadata for the 17 Unicode planes. Planes 4–13 are
|
|
17
17
|
# unassigned in Unicode 17; their entries use placeholder names.
|
|
18
18
|
PLANE_TABLE = {
|
|
19
|
-
0
|
|
20
|
-
1
|
|
21
|
-
2
|
|
22
|
-
3
|
|
23
|
-
4
|
|
24
|
-
5
|
|
25
|
-
6
|
|
26
|
-
7
|
|
27
|
-
8
|
|
28
|
-
9
|
|
19
|
+
0 => ["Basic Multilingual Plane", "BMP"],
|
|
20
|
+
1 => ["Supplementary Multilingual Plane", "SMP"],
|
|
21
|
+
2 => ["Supplementary Ideographic Plane", "SIP"],
|
|
22
|
+
3 => ["Tertiary Ideographic Plane", "TIP"],
|
|
23
|
+
4 => ["Unassigned Plane 4", "—"],
|
|
24
|
+
5 => ["Unassigned Plane 5", "—"],
|
|
25
|
+
6 => ["Unassigned Plane 6", "—"],
|
|
26
|
+
7 => ["Unassigned Plane 7", "—"],
|
|
27
|
+
8 => ["Unassigned Plane 8", "—"],
|
|
28
|
+
9 => ["Unassigned Plane 9", "—"],
|
|
29
29
|
10 => ["Unassigned Plane 10", "—"],
|
|
30
30
|
11 => ["Unassigned Plane 11", "—"],
|
|
31
31
|
12 => ["Unassigned Plane 12", "—"],
|
|
@@ -68,15 +68,15 @@ module Ucode
|
|
|
68
68
|
range_first = plane_number * 0x10000
|
|
69
69
|
range_last = range_first + 0xFFFF
|
|
70
70
|
to_pretty_json(
|
|
71
|
-
"number"
|
|
72
|
-
"name"
|
|
73
|
-
"abbrev"
|
|
74
|
-
"range_first"
|
|
75
|
-
"range_last"
|
|
76
|
-
"block_ids"
|
|
71
|
+
"number" => plane_number,
|
|
72
|
+
"name" => name,
|
|
73
|
+
"abbrev" => abbrev,
|
|
74
|
+
"range_first" => range_first,
|
|
75
|
+
"range_last" => range_last,
|
|
76
|
+
"block_ids" => block_ids,
|
|
77
77
|
)
|
|
78
78
|
end
|
|
79
79
|
end
|
|
80
80
|
end
|
|
81
81
|
end
|
|
82
|
-
end
|
|
82
|
+
end
|
|
@@ -41,14 +41,14 @@ module Ucode
|
|
|
41
41
|
|
|
42
42
|
def script_payload(code, ranges)
|
|
43
43
|
to_pretty_json(
|
|
44
|
-
"code"
|
|
45
|
-
"name"
|
|
46
|
-
"range_first"
|
|
47
|
-
"range_last"
|
|
48
|
-
"codepoint_ids"
|
|
44
|
+
"code" => code,
|
|
45
|
+
"name" => ranges.first&.name,
|
|
46
|
+
"range_first" => ranges.map(&:range_first).min,
|
|
47
|
+
"range_last" => ranges.map(&:range_last).max,
|
|
48
|
+
"codepoint_ids" => @script_codepoint_ids[code] || [],
|
|
49
49
|
)
|
|
50
50
|
end
|
|
51
51
|
end
|
|
52
52
|
end
|
|
53
53
|
end
|
|
54
|
-
end
|
|
54
|
+
end
|
data/lib/ucode/repo/writers.rb
CHANGED
data/lib/ucode/version.rb
CHANGED
data/lib/ucode.rb
CHANGED
|
@@ -30,11 +30,13 @@ module Ucode
|
|
|
30
30
|
autoload :DatabaseMissingError, "ucode/error"
|
|
31
31
|
autoload :DatabaseSchemaError, "ucode/error"
|
|
32
32
|
autoload :UnknownVersionError, "ucode/error"
|
|
33
|
+
autoload :UnknownBlockError, "ucode/error"
|
|
33
34
|
autoload :GlyphError, "ucode/error"
|
|
34
35
|
autoload :PdfRenderError, "ucode/error"
|
|
35
36
|
autoload :GridDetectionError, "ucode/error"
|
|
36
37
|
autoload :LastResortMissingError, "ucode/error"
|
|
37
38
|
autoload :EmbeddedFontsMissingError, "ucode/error"
|
|
39
|
+
autoload :CodeChartNotFoundError, "ucode/error"
|
|
38
40
|
|
|
39
41
|
# Infrastructure
|
|
40
42
|
autoload :Cache, "ucode/cache"
|
|
@@ -54,6 +56,7 @@ module Ucode
|
|
|
54
56
|
autoload :Repo, "ucode/repo"
|
|
55
57
|
autoload :Glyphs, "ucode/glyphs"
|
|
56
58
|
autoload :Audit, "ucode/audit"
|
|
59
|
+
autoload :CodeChart, "ucode/code_chart"
|
|
57
60
|
autoload :Site, "ucode/site"
|
|
58
61
|
autoload :Commands, "ucode/commands"
|
|
59
62
|
autoload :Cli, "ucode/cli"
|
data/ucode.gemspec
CHANGED
|
@@ -45,7 +45,12 @@ Gem::Specification.new do |spec|
|
|
|
45
45
|
spec.require_paths = ["lib"]
|
|
46
46
|
|
|
47
47
|
spec.add_dependency "base64"
|
|
48
|
-
|
|
48
|
+
# Pin fontisan to 0.2.22 — 0.2.23+ removed
|
|
49
|
+
# `Fontisan::Commands::AuditCommand` (used by RealFonts::CoverageAuditor)
|
|
50
|
+
# and 0.4.x removed the entire Audit subsystem. Until
|
|
51
|
+
# CoverageAuditor is rewritten against the new fontisan API, this
|
|
52
|
+
# pin keeps the existing audit path working.
|
|
53
|
+
spec.add_dependency "fontisan", "= 0.2.22"
|
|
49
54
|
spec.add_dependency "fontist", "~> 3.0"
|
|
50
55
|
spec.add_dependency "logger"
|
|
51
56
|
spec.add_dependency "lutaml-model", "~> 0.8"
|
metadata
CHANGED
|
@@ -1,14 +1,14 @@
|
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
|
2
2
|
name: ucode
|
|
3
3
|
version: !ruby/object:Gem::Version
|
|
4
|
-
version: 0.2.
|
|
4
|
+
version: 0.2.2
|
|
5
5
|
platform: ruby
|
|
6
6
|
authors:
|
|
7
7
|
- Ribose Inc.
|
|
8
8
|
autorequire:
|
|
9
9
|
bindir: exe
|
|
10
10
|
cert_chain: []
|
|
11
|
-
date: 2026-
|
|
11
|
+
date: 2026-07-01 00:00:00.000000000 Z
|
|
12
12
|
dependencies:
|
|
13
13
|
- !ruby/object:Gem::Dependency
|
|
14
14
|
name: base64
|
|
@@ -28,16 +28,16 @@ dependencies:
|
|
|
28
28
|
name: fontisan
|
|
29
29
|
requirement: !ruby/object:Gem::Requirement
|
|
30
30
|
requirements:
|
|
31
|
-
- -
|
|
31
|
+
- - '='
|
|
32
32
|
- !ruby/object:Gem::Version
|
|
33
|
-
version:
|
|
33
|
+
version: 0.2.22
|
|
34
34
|
type: :runtime
|
|
35
35
|
prerelease: false
|
|
36
36
|
version_requirements: !ruby/object:Gem::Requirement
|
|
37
37
|
requirements:
|
|
38
|
-
- -
|
|
38
|
+
- - '='
|
|
39
39
|
- !ruby/object:Gem::Version
|
|
40
|
-
version:
|
|
40
|
+
version: 0.2.22
|
|
41
41
|
- !ruby/object:Gem::Dependency
|
|
42
42
|
name: fontist
|
|
43
43
|
requirement: !ruby/object:Gem::Requirement
|
|
@@ -156,6 +156,14 @@ files:
|
|
|
156
156
|
- Gemfile
|
|
157
157
|
- README.md
|
|
158
158
|
- Rakefile
|
|
159
|
+
- TODO.extract-code-chart/01-pdf-fetch-validation.md
|
|
160
|
+
- TODO.extract-code-chart/02-block-name-resolver.md
|
|
161
|
+
- TODO.extract-code-chart/03-codechart-namespace.md
|
|
162
|
+
- TODO.extract-code-chart/04-codechart-extractor.md
|
|
163
|
+
- TODO.extract-code-chart/05-provenance-and-sidecar.md
|
|
164
|
+
- TODO.extract-code-chart/06-codechart-writer.md
|
|
165
|
+
- TODO.extract-code-chart/07-codechart-cli.md
|
|
166
|
+
- TODO.extract-code-chart/08-specs.md
|
|
159
167
|
- TODO.full/00-README.md
|
|
160
168
|
- TODO.full/01-panglyph-vision.md
|
|
161
169
|
- TODO.full/02-panglyph-repo-bootstrap.md
|
|
@@ -295,6 +303,11 @@ files:
|
|
|
295
303
|
- lib/ucode/audit/universal_set_reference.rb
|
|
296
304
|
- lib/ucode/cache.rb
|
|
297
305
|
- lib/ucode/cli.rb
|
|
306
|
+
- lib/ucode/code_chart.rb
|
|
307
|
+
- lib/ucode/code_chart/extractor.rb
|
|
308
|
+
- lib/ucode/code_chart/provenance.rb
|
|
309
|
+
- lib/ucode/code_chart/sidecar.rb
|
|
310
|
+
- lib/ucode/code_chart/writer.rb
|
|
298
311
|
- lib/ucode/commands.rb
|
|
299
312
|
- lib/ucode/commands/audit.rb
|
|
300
313
|
- lib/ucode/commands/audit/browser_command.rb
|