Subset fonts to used character data

Makefile

@@ -26,6 +26,7 @@ ARTIFACT_DESTINATION_FILE ?= ./tmp/idp.tar.gz
 	lint_analytics_events_sorted \
 	lint_country_dialing_codes \
 	lint_erb \
+	lint_font_glyphs \
 	lint_lockfiles \
 	lint_new_typescript_files \
 	lint_optimized_assets \
@@ -87,6 +88,8 @@ endif
 	# Other
 	@echo "--- lint yaml ---"
 	make lint_yaml
+	@echo "--- lint font glyphs ---"
+	make lint_font_glyphs
 	@echo "--- lint Yarn workspaces ---"
 	make lint_yarn_workspaces
 	@echo "--- lint new TypeScript files ---"
@@ -110,6 +113,15 @@ lint_erb: ## Lints ERB files
 lint_yaml: normalize_yaml ## Lints YAML files
 	(! git diff --name-only | grep "^config/.*\.yml$$") || (echo "Error: Run 'make normalize_yaml' to normalize YAML"; exit 1)
 
+lint_font_glyphs: ## Lints to validate content glyphs match expectations from fonts
+	scripts/yaml_characters \
+		--exclude-locale=zh \
+		--exclude-gem-path=faker \
+		--exclude-gem-path=good_job \
+		--exclude-gem-path=i18n-tasks \
+		> app/assets/fonts/glyphs.txt
+	(! git diff --name-only | grep "glyphs\.txt$$") || (echo "Error: New character data found. Follow 'Fonts' instructions in 'docs/frontend.md' to regenerate fonts."; exit 1)
+
 lint_yarn_workspaces: ## Lints Yarn workspace packages
 	scripts/validate-workspaces.mjs
 

app/assets/fonts/glyphs.txt

@@ -0,0 +1 @@
+ !"#$%&'(),-./0123456789:;>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ_abcdefghijklmnopqrstuvwxyz~ «»¿ÀÁÈÉÊÎÓÚàáâãçèéêëíîïñóôùúû ‑—‘’“”…‹中体文简

docs/frontend.md

@@ -390,6 +390,24 @@ Debugging these stack traces can be difficult, since files in production are min
 
 The output of the `sourcemap-lookup` command should include "Original Position" and "Code Section" of the code which triggered the error.
 
+## Fonts
+
+Font files are optimized to remove unused character data. If a new character is added to content, the font files must be regenerated:
+
+1. [Download Public Sans](https://public-sans.digital.gov/) and extract it to your project's `tmp/` directory
+2. Install [glyphhanger](https://github.com/zachleat/glyphhanger) and its dependencies:
+   1. `npm install -g glyphhanger`
+   2. `pip install fonttools brotli`
+3. Scrape content for character data:
+   1. `make lint_font_glyphs`
+4. Subset the original Public Sans fonts to include only used character data:
+   1. `glyphhanger app/assets/fonts/glyphs.txt --formats=woff2 --subset="tmp/public-sans-v2/fonts/ttf/PublicSans-*.ttf"`
+5. Replace font files with new subset fonts:
+   1. `cd tmp/public-sans-v2/fonts/ttf`
+   2. `find . -name "*-subset.woff2" -exec sh -c 'cp $1 "../../../../app/assets/fonts/public-sans/${1%-subset.woff2}.woff2"' _ {} \;`
+
+At this point, your working directory should reflect changes to all of the files within `app/assets/fonts/public-sans`.
+
 ## Devices
 
 The application should support:

scripts/yaml_characters

@@ -0,0 +1,64 @@
+#!/usr/bin/env ruby
+# frozen_string_literal: true
+
+require 'pathname'
+require_relative '../config/environment'
+
+excluded_locales = []
+excluded_gem_paths = []
+OptionParser.new do |opts|
+  opts.banner = <<~TXT
+    Usage
+    =======================
+
+      #{$PROGRAM_NAME} [OPTIONS]
+
+      Prints all unique characters from Rails loaded I18n data, which can be used in combination
+      with font subsetting to optimize font sizes.
+
+  TXT
+
+  opts.on('--exclude-locale=LOCALE', 'Disregard characters from the given locale') do |locale|
+    excluded_locales << locale.to_sym
+  end
+
+  opts.on('--exclude-gem-path=GEM', 'Disregard characters loaded by the given gem') do |gem|
+    excluded_gem_paths << Gem.loaded_specs[gem].full_gem_path
+  end
+
+  opts.on('-h', '--help', 'Prints this help') do
+    STDOUT.puts opts
+    exit
+  end
+end.parse!(ARGV)
+
+def sanitize(string)
+  string.gsub(/<.+?>/, '').gsub(/%{.+?}/, '').gsub(/[\n\r\t]/, '')
+end
+
+def hash_values(hash)
+  hash.values.flat_map do |value|
+    case value
+    when Hash
+      hash_values(value)
+    when Array
+      value
+    else
+      [value]
+    end
+  end
+end
+
+I18n.load_path.reject! do |load_path|
+  excluded_gem_paths.any? { |gem_path| load_path.start_with?(gem_path) }
+end
+
+I18n.backend.eager_load!
+
+data = I18n.backend.translations.slice(*I18n.available_locales - excluded_locales)
+strings = hash_values(data)
+joined_string = strings.join('')
+sanitized_string = sanitize(joined_string)
+characters = sanitized_string.chars.to_a.uniq.sort.join('')
+
+STDOUT.puts characters