ucode 0.1.0 → 0.1.1

data/schema/block-feed.output.schema.yml

@@ -0,0 +1,134 @@
+# ucode block-feed output schema
+#
+# This is the canonical shape of ucode's `block-feed` output — a compact
+# per-block Unicode data feed derived from ucode's canonical output tree.
+#
+# ucode emits three files under the target directory:
+#
+#   unicode-blocks.json
+#   unicode-version.json
+#   unicode/blocks/<slug>.json
+#
+# Block slugs are derived from the Unicode block display name via the
+# standard slug algorithm:
+#
+#   name.downcase.gsub(/[^a-z0-9]+/, "-").gsub(/^-|-$/, "")
+#
+# Field names are short (cp, n, c, s, cc, bc, mir) because the per-block
+# files inline every codepoint — byte size matters at the long tail
+# (CJK Unified Ideographs alone is 20,992 chars in one file).
+#
+# This schema describes Unicode data only. It is not specific to any
+# consumer; any tooling that wants a compact per-block view of Unicode
+# can consume it.
+
+$schema: "https://json-schema.org/draft/2020-12/schema"
+title: UcodeBlockFeed
+description: Canonical shape of ucode's compact per-block Unicode data feed
+
+definitions:
+
+  codepoint:
+    description: A single Unicode codepoint's compact metadata.
+    type: object
+    additionalProperties: false
+    required: [cp]
+    properties:
+      cp:
+        type: integer
+        minimum: 0
+        maximum: 0x10FFFF
+        description: The Unicode scalar value (integer form of U+XXXX).
+      n:
+        type: string
+        minLength: 1
+        description: Codepoint name (e.g. "LATIN CAPITAL LETTER A"). Omitted when empty.
+      c:
+        type: string
+        minLength: 1
+        pattern: '^[A-Z][a-z]$'
+        description: General category short code (Lu, Ll, Mn, So, ...).
+      s:
+        type: string
+        minLength: 2
+        description: Script code (Latn, Grek, Hani, Zyyy, ...). 4-letter ISO 15924.
+      cc:
+        type: integer
+        minimum: 0
+        maximum: 255
+        description: Canonical combining class. Always present (0 for non-marks).
+      bc:
+        type: string
+        minLength: 1
+        description: Bidi class short code (L, R, AL, AN, NSM, BN, ...).
+      mir:
+        type: boolean
+        description: Bidi mirrored flag. Omitted when false.
+
+  block_summary:
+    description: One entry per Unicode block in unicode-blocks.json.
+    type: object
+    additionalProperties: false
+    required: [start, end, name, unicode_version]
+    properties:
+      start:
+        type: integer
+        minimum: 0
+        maximum: 0x10FFFF
+        description: First codepoint in the block (inclusive).
+      end:
+        type: integer
+        minimum: 0
+        maximum: 0x10FFFF
+        description: Last codepoint in the block (inclusive).
+      name:
+        type: string
+        minLength: 1
+        description: Unicode block display name (e.g. "Basic Latin", "Greek and Coptic").
+      unicode_version:
+        type: string
+        pattern: '^\d+\.\d+\.\d+$'
+        description: Earliest Unicode version of any codepoint in the block (e.g. "1.1", "17.0.0").
+
+type: object
+properties:
+
+  unicode-blocks.json:
+    type: array
+    description: Top-level index of all Unicode blocks (~346 entries for Unicode 17).
+    items:
+      $ref: '#/definitions/block_summary'
+
+  unicode-version.json:
+    type: object
+    additionalProperties: false
+    required: [version, blockCount, charCount, generatedAt]
+    properties:
+      version:
+        type: string
+        pattern: '^\d+\.\d+\.\d+$'
+        description: UCD version (e.g. "17.0.0").
+      blockCount:
+        type: integer
+        minimum: 1
+        description: Total number of blocks (must match length of unicode-blocks.json).
+      charCount:
+        type: integer
+        minimum: 1
+        description: Total assigned codepoints across all blocks.
+      generatedAt:
+        type: string
+        format: date-time
+        description: ISO 8601 timestamp of the emitter run.
+
+  unicode/blocks/<slug>.json:
+    type: object
+    additionalProperties: false
+    required: [chars]
+    properties:
+      chars:
+        type: array
+        minItems: 0
+        description: Codepoints in this block, ordered by cp ascending.
+        items:
+          $ref: '#/definitions/codepoint'

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: ucode
 version: !ruby/object:Gem::Version
-  version: 0.1.0
+  version: 0.1.1
 platform: ruby
 authors:
 - Ribose Inc.
@@ -150,11 +150,33 @@ executables:
 extensions: []
 extra_rdoc_files: []
 files:
+- CHANGELOG.md
 - CLAUDE.md
 - Gemfile
 - Gemfile.lock
 - README.md
 - Rakefile
+- TODO.full/00-README.md
+- TODO.full/01-panglyph-vision.md
+- TODO.full/02-panglyph-repo-bootstrap.md
+- TODO.full/03-panglyph-font-builder.md
+- TODO.full/04-panglyph-publish-pipeline.md
+- TODO.full/05-ucode-0-1-1-release.md
+- TODO.full/06-fontisan-remove-audit.md
+- TODO.full/07-fontisan-remove-ucd.md
+- TODO.full/08-archive-private-bin-build.md
+- TODO.full/09-archive-public-structure.md
+- TODO.full/10-fontist-org-woff-glyphs.md
+- TODO.full/11-fontist-org-audit-coverage.md
+- TODO.full/12-implementation-order.md
+- TODO.full/13-fontisan-font-writer-api.md
+- TODO.full/14-fontisan-table-writers.md
+- TODO.full/15-panglyph-builder-real.md
+- TODO.full/16-archive-public-sync-workflows.md
+- TODO.full/17-fontist-org-font-picker.md
+- TODO.full/18-comprehensive-spec-coverage.md
+- TODO.full/19-ucode-0-1-2-patch.md
+- TODO.full/20-fontisan-0-2-23-release.md
 - TODO.new/00-README.md
 - TODO.new/01-pillar-terminology-alignment.md
 - TODO.new/02-audit-schema-design.md
@@ -178,15 +200,65 @@ files:
 - TODO.new/20-canonical-resolver-4-tier.md
 - TODO.new/21-canonical-unicode17-build.md
 - TODO.new/22-implementation-order.md
+- TODO.new/23-universal-glyph-set-source-map.md
+- TODO.new/24-universal-glyph-set-build.md
+- TODO.new/25-font-audit-against-universal-set.md
+- TODO.new/26-missing-glyph-reporter.md
+- TODO.new/27-fontist-org-consumer-integration.md
+- TODO.new/28-implementation-order-update.md
+- TODO.new/29-universal-set-curation-uc17.md
+- TODO.new/30-tier1-font-acquisition.md
+- TODO.new/31-universal-set-production-build.md
+- TODO.new/32-uc17-coverage-matrix.md
+- TODO.new/33-specialist-font-acquisition-refresh.md
+- TODO.new/34-pillar2-content-stream-correlator.md
+- TODO.new/35-universal-set-production-run.md
+- TODO.new/36-per-font-coverage-audit.md
+- TODO.new/37-coverage-highlight-reporter.md
+- TODO.new/38-fontist-org-glyph-consumer.md
+- TODO.new/39-implementation-order-update-32-38.md
+- TODO.new/40-archive-private-uses-ucode-audit.md
+- TODO.new/41-ucode-unicode-archive-bridge.md
 - UCODE_CHANGELOG.md
+- config/specialist_fonts.yml
+- config/unicode17_tier1_fonts.yml
+- config/unicode17_universal_glyph_set.yml
 - exe/ucode
 - lib/ucode.rb
 - lib/ucode/aggregator.rb
 - lib/ucode/audit.rb
 - lib/ucode/audit/block_aggregator.rb
+- lib/ucode/audit/browser.rb
+- lib/ucode/audit/browser/face_page.rb
+- lib/ucode/audit/browser/glyph_panel.rb
+- lib/ucode/audit/browser/library_page.rb
+- lib/ucode/audit/browser/missing_glyph_page.rb
+- lib/ucode/audit/browser/template.rb
+- lib/ucode/audit/browser/templates/face.css
+- lib/ucode/audit/browser/templates/face.html.erb
+- lib/ucode/audit/browser/templates/face.js
+- lib/ucode/audit/browser/templates/library.css
+- lib/ucode/audit/browser/templates/library.html.erb
+- lib/ucode/audit/browser/templates/library.js
+- lib/ucode/audit/browser/templates/missing_glyph_page.css
+- lib/ucode/audit/browser/templates/missing_glyph_page.html.erb
+- lib/ucode/audit/browser/templates/missing_glyph_page.js
 - lib/ucode/audit/codepoint_range_coalescer.rb
 - lib/ucode/audit/context.rb
+- lib/ucode/audit/coverage_reference.rb
+- lib/ucode/audit/differ.rb
 - lib/ucode/audit/discrepancy_detector.rb
+- lib/ucode/audit/emitter.rb
+- lib/ucode/audit/emitter/block_emitter.rb
+- lib/ucode/audit/emitter/codepoint_emitter.rb
+- lib/ucode/audit/emitter/collection_emitter.rb
+- lib/ucode/audit/emitter/face_directory.rb
+- lib/ucode/audit/emitter/glyph_emitter.rb
+- lib/ucode/audit/emitter/index_emitter.rb
+- lib/ucode/audit/emitter/library_emitter.rb
+- lib/ucode/audit/emitter/paths.rb
+- lib/ucode/audit/emitter/plane_emitter.rb
+- lib/ucode/audit/emitter/script_emitter.rb
 - lib/ucode/audit/extractors.rb
 - lib/ucode/audit/extractors/aggregations.rb
 - lib/ucode/audit/extractors/base.rb
@@ -200,20 +272,48 @@ files:
 - lib/ucode/audit/extractors/provenance.rb
 - lib/ucode/audit/extractors/style.rb
 - lib/ucode/audit/extractors/variation_detail.rb
+- lib/ucode/audit/face_auditor.rb
+- lib/ucode/audit/formatters.rb
+- lib/ucode/audit/formatters/audit_diff_text.rb
+- lib/ucode/audit/formatters/audit_text.rb
+- lib/ucode/audit/formatters/color.rb
+- lib/ucode/audit/formatters/library_summary_text.rb
+- lib/ucode/audit/formatters/text_formatter.rb
+- lib/ucode/audit/library_aggregator.rb
+- lib/ucode/audit/library_auditor.rb
 - lib/ucode/audit/plane_aggregator.rb
 - lib/ucode/audit/registry.rb
+- lib/ucode/audit/release.rb
+- lib/ucode/audit/release/emitter.rb
+- lib/ucode/audit/release/face_card.rb
+- lib/ucode/audit/release/formula_audits.rb
+- lib/ucode/audit/release/library_index_builder.rb
+- lib/ucode/audit/release/manifest_builder.rb
 - lib/ucode/audit/script_aggregator.rb
+- lib/ucode/audit/ucd_only_reference.rb
+- lib/ucode/audit/universal_set_reference.rb
 - lib/ucode/cache.rb
 - lib/ucode/cli.rb
 - lib/ucode/commands.rb
+- lib/ucode/commands/audit.rb
+- lib/ucode/commands/audit/browser_command.rb
+- lib/ucode/commands/audit/collection_command.rb
+- lib/ucode/commands/audit/compare_command.rb
+- lib/ucode/commands/audit/font_command.rb
+- lib/ucode/commands/audit/library_command.rb
+- lib/ucode/commands/audit/reference_builder.rb
+- lib/ucode/commands/block_feed.rb
 - lib/ucode/commands/build.rb
 - lib/ucode/commands/cache.rb
+- lib/ucode/commands/canonical_build.rb
 - lib/ucode/commands/fetch.rb
 - lib/ucode/commands/font_coverage.rb
 - lib/ucode/commands/glyphs.rb
 - lib/ucode/commands/lookup.rb
 - lib/ucode/commands/parse.rb
+- lib/ucode/commands/release.rb
 - lib/ucode/commands/site.rb
+- lib/ucode/commands/universal_set.rb
 - lib/ucode/config.rb
 - lib/ucode/coordinator.rb
 - lib/ucode/coordinator/indices.rb
@@ -222,7 +322,10 @@ files:
 - lib/ucode/error.rb
 - lib/ucode/fetch.rb
 - lib/ucode/fetch/code_charts.rb
+- lib/ucode/fetch/font_fetcher.rb
+- lib/ucode/fetch/font_fetcher/result.rb
 - lib/ucode/fetch/http.rb
+- lib/ucode/fetch/specialist_font_fetcher.rb
 - lib/ucode/fetch/ucd_zip.rb
 - lib/ucode/fetch/unihan_zip.rb
 - lib/ucode/glyphs.rb
@@ -256,11 +359,30 @@ files:
 - lib/ucode/glyphs/pdftocairo_renderer.rb
 - lib/ucode/glyphs/real_fonts.rb
 - lib/ucode/glyphs/real_fonts/block_coverage.rb
+- lib/ucode/glyphs/real_fonts/cmap_cache.rb
 - lib/ucode/glyphs/real_fonts/coverage_auditor.rb
 - lib/ucode/glyphs/real_fonts/font_coverage_report.rb
 - lib/ucode/glyphs/real_fonts/font_locator.rb
 - lib/ucode/glyphs/real_fonts/unicode_17_blocks.rb
 - lib/ucode/glyphs/real_fonts/writer.rb
+- lib/ucode/glyphs/resolver.rb
+- lib/ucode/glyphs/source.rb
+- lib/ucode/glyphs/source_builder.rb
+- lib/ucode/glyphs/source_config.rb
+- lib/ucode/glyphs/source_config/coverage_assertion.rb
+- lib/ucode/glyphs/source_config/gap_report.rb
+- lib/ucode/glyphs/sources.rb
+- lib/ucode/glyphs/sources/pillar1_embedded_tounicode.rb
+- lib/ucode/glyphs/sources/pillar3_last_resort.rb
+- lib/ucode/glyphs/sources/tier1_real_font.rb
+- lib/ucode/glyphs/universal_set.rb
+- lib/ucode/glyphs/universal_set/builder.rb
+- lib/ucode/glyphs/universal_set/coverage_report.rb
+- lib/ucode/glyphs/universal_set/idempotency.rb
+- lib/ucode/glyphs/universal_set/manifest_accumulator.rb
+- lib/ucode/glyphs/universal_set/manifest_writer.rb
+- lib/ucode/glyphs/universal_set/pre_build_check.rb
+- lib/ucode/glyphs/universal_set/validator.rb
 - lib/ucode/glyphs/writer.rb
 - lib/ucode/index.rb
 - lib/ucode/index_builder.rb
@@ -272,6 +394,7 @@ files:
 - lib/ucode/models/audit/baseline.rb
 - lib/ucode/models/audit/block_summary.rb
 - lib/ucode/models/audit/codepoint_detail.rb
+- lib/ucode/models/audit/codepoint_provenance.rb
 - lib/ucode/models/audit/codepoint_range.rb
 - lib/ucode/models/audit/codepoint_set_diff.rb
 - lib/ucode/models/audit/color_capabilities.rb
@@ -288,6 +411,10 @@ files:
 - lib/ucode/models/audit/named_instance.rb
 - lib/ucode/models/audit/opentype_layout.rb
 - lib/ucode/models/audit/plane_summary.rb
+- lib/ucode/models/audit/release_face.rb
+- lib/ucode/models/audit/release_formula.rb
+- lib/ucode/models/audit/release_manifest.rb
+- lib/ucode/models/audit/release_universal_set.rb
 - lib/ucode/models/audit/script_coverage_row.rb
 - lib/ucode/models/audit/script_features.rb
 - lib/ucode/models/audit/script_summary.rb
@@ -296,6 +423,7 @@ files:
 - lib/ucode/models/bidi_mirroring.rb
 - lib/ucode/models/binary_property_assignment.rb
 - lib/ucode/models/block.rb
+- lib/ucode/models/build_report.rb
 - lib/ucode/models/case_folding_rule.rb
 - lib/ucode/models/cjk_radical.rb
 - lib/ucode/models/codepoint.rb
@@ -306,12 +434,15 @@ files:
 - lib/ucode/models/codepoint/decomposition.rb
 - lib/ucode/models/codepoint/display.rb
 - lib/ucode/models/codepoint/emoji.rb
+- lib/ucode/models/codepoint/glyph.rb
 - lib/ucode/models/codepoint/hangul.rb
 - lib/ucode/models/codepoint/identifier.rb
 - lib/ucode/models/codepoint/indic.rb
 - lib/ucode/models/codepoint/joining.rb
 - lib/ucode/models/codepoint/normalization.rb
 - lib/ucode/models/codepoint/numeric_value.rb
+- lib/ucode/models/glyph_source.rb
+- lib/ucode/models/glyph_source_map.rb
 - lib/ucode/models/name_alias.rb
 - lib/ucode/models/named_sequence.rb
 - lib/ucode/models/names_list_entry.rb
@@ -327,8 +458,14 @@ files:
 - lib/ucode/models/relationship/variation_sequence.rb
 - lib/ucode/models/script.rb
 - lib/ucode/models/special_casing_rule.rb
+- lib/ucode/models/specialist_font.rb
+- lib/ucode/models/specialist_font_manifest.rb
 - lib/ucode/models/standardized_variant.rb
 - lib/ucode/models/unihan_entry.rb
+- lib/ucode/models/unihan_field.rb
+- lib/ucode/models/universal_set_entry.rb
+- lib/ucode/models/universal_set_manifest.rb
+- lib/ucode/models/validation_report.rb
 - lib/ucode/parsers.rb
 - lib/ucode/parsers/auxiliary.rb
 - lib/ucode/parsers/base.rb
@@ -356,6 +493,10 @@ files:
 - lib/ucode/repo.rb
 - lib/ucode/repo/aggregate_writer.rb
 - lib/ucode/repo/atomic_writes.rb
+- lib/ucode/repo/block_feed_emitter.rb
+- lib/ucode/repo/build_report_accumulator.rb
+- lib/ucode/repo/build_report_writer.rb
+- lib/ucode/repo/build_validator.rb
 - lib/ucode/repo/codepoint_writer.rb
 - lib/ucode/repo/paths.rb
 - lib/ucode/site.rb
@@ -375,7 +516,7 @@ files:
 - lib/ucode/site/template/search.md
 - lib/ucode/version.rb
 - lib/ucode/version_resolver.rb
-- ucode.gemspec
+- schema/block-feed.output.schema.yml
 homepage: https://github.com/fontist/ucode
 licenses:
 - BSD-2-Clause

data/ucode.gemspec

@@ -1,56 +0,0 @@
-# frozen_string_literal: true
-
-require_relative "lib/ucode/version"
-
-Gem::Specification.new do |spec|
-  spec.name = "ucode"
-  spec.version = Ucode::VERSION
-  spec.authors = ["Ribose Inc."]
-  spec.email = ["open.source@ribose.com"]
-
-  spec.summary = "Unicode Character Database toolkit — lookup, dataset, glyphs, site"
-  spec.description = <<~DESC
-    ucode turns the Unicode Character Database (UCD) text files and the official
-    Unicode Code Charts into a structured, browsable dataset. For every assigned
-    codepoint it produces a JSON document with full UCD properties, the
-    human-curated relationships from NamesList.txt, Unihan readings, and
-    machine-computed references; an SVG of the official glyph vector-extracted
-    from the Code Charts; and a Vitepress site for browsing Plane, Block,
-    and Character.
-  DESC
-
-  spec.homepage = "https://github.com/fontist/ucode"
-  spec.license = "BSD-2-Clause"
-  spec.required_ruby_version = ">= 3.2.0"
-
-  spec.metadata["homepage_uri"] = spec.homepage
-  spec.metadata["source_code_uri"] = "https://github.com/fontist/ucode"
-  spec.metadata["changelog_uri"] = "https://github.com/fontist/ucode/blob/main/CHANGELOG.md"
-  spec.metadata["rubygems_mfa_required"] = "true"
-
-  spec.files = Dir.chdir(__dir__) do
-    `git ls-files -z`.split("\x0").reject do |f|
-      f == __FILE__ ||
-        f.start_with?(".") ||
-        f.start_with?("spec/") ||
-        f.start_with?("benchmark/") ||
-        f.start_with?("TODO.impl/") ||
-        f.start_with?("docs/") ||
-        f.start_with?("site/")
-    end
-  end
-
-  spec.bindir = "exe"
-  spec.executables = spec.files.grep(%r{\Aexe/}) { |f| File.basename(f) }
-  spec.require_paths = ["lib"]
-
-  spec.add_dependency "base64"
-  spec.add_dependency "fontisan", "~> 0.2"
-  spec.add_dependency "fontist", "~> 3.0"
-  spec.add_dependency "logger"
-  spec.add_dependency "lutaml-model", "~> 0.8"
-  spec.add_dependency "nokogiri", "~> 1.16"
-  spec.add_dependency "rubyzip", "~> 2.3"
-  spec.add_dependency "sqlite3", "~> 2.0"
-  spec.add_dependency "thor", "~> 1.3"
-end