rsyntaxtree 1.7.0 → 1.8.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 4b011905bb833561ebbc545ce04c4c6cf104290298fc6b2018d09f8c9ef58383
-  data.tar.gz: 7f35db88fa0d6585f6832d6d6621b527e830c5d7772ddb3282ccf1341b990c16
+  metadata.gz: 9b9513e8d667af90de0a12e427eae11d0089f6a969ed1a47714ca30401001821
+  data.tar.gz: '0458b65b7f9ad1f495d344963b41b801b7c26562b0256abe48885756a1481bef'
 SHA512:
-  metadata.gz: 7d96fe35d241eb21bb3248dd9b566a5dd0603bbed8f7118579f915ef9eecb3d875f10508dbdb4ec09f8fffa53ec2a86cb7d9d3d7458dba86f799ff1505f70fd0
-  data.tar.gz: 9e2298a797787e12407e57d0dc05e59cbb444b6b0792c6be1447190ef99fae4899a2ead1df2d40e80f26615d268ce0e3287029db002c02c1344aceed2a5d7bf5
+  metadata.gz: d1738b00df2a2dbe5cafba5d52b19c44149472912c2859c8183384582770be0b54c0c4e96688fe4c0a808969c96096504956b7ce7dffc76bd3c682ee28124cf6
+  data.tar.gz: a8363b3b3e6b11f345603f020e36766275f740ab0f80af4ecb4be3f9160dd7860d4a26c4cdd2788a8b02e27d4c99d1147bd9843200cdd41cf48f87b6ce373e34

data/.github/workflows/test.yml

@@ -0,0 +1,35 @@
+name: Test
+
+on:
+  push:
+    branches: [master]
+  pull_request:
+    branches: [master]
+  workflow_dispatch:
+
+jobs:
+  test:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        ruby-version: ["3.2", "3.4"]
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Install system dependencies
+        run: |
+          sudo apt-get update
+          sudo apt-get install -y \
+            libpango1.0-dev librsvg2-dev libmagickwand-dev \
+            libgirepository1.0-dev gobject-introspection \
+            fonts-noto-core fonts-noto-cjk
+          sudo fc-cache -f
+
+      - name: Set up Ruby ${{ matrix.ruby-version }}
+        uses: ruby/setup-ruby@v1
+        with:
+          ruby-version: ${{ matrix.ruby-version }}
+          bundler-cache: true
+
+      - name: Run tests
+        run: bundle exec rake test

data/CHANGELOG.md

@@ -1,5 +1,81 @@
 # Changelog
 
+## [1.8.1] - 2026-08
+
+### Fixed
+- Arabic rendered as isolated, unjoined letterforms in some environments.
+  Scripts outside Latin and CJK were left to the system's generic font
+  fallback, which is not the same font on every machine: on Alpine the Arabic
+  block was claimed by Noto Sans Math, which has the glyphs but no joining
+  rules, while on Debian the same text fell to DejaVu Sans. The family chains
+  now name the scripts the gallery covers — Arabic (`Noto Sans Arabic`, with
+  `Noto Naskh Arabic` for the serif style), Hebrew, Devanagari, Thai and
+  Khmer — so the same input renders the same way everywhere. Gallery example
+  067 (Arabic) was affected and has been regenerated.
+- Emoji were measured with one font and drawn with another where a colour
+  emoji font was installed: Pango selects `Noto Color Emoji`, but the
+  librsvg/Cairo pipeline does not rasterise its bitmap glyphs, so the drawing
+  fell back to whatever outline font happened to cover the codepoint. The
+  project's Docker images now install the monochrome Noto Emoji and leave the
+  colour build out.
+
+### Changed
+- The Docker images install the Noto packages for Arabic (including Naskh),
+  Hebrew, Devanagari, Thai and Khmer, and carry a fontconfig rule that removes
+  the Arabic ranges from Noto Sans Math while keeping its mathematical
+  alphanumerics (used for the little *v* of *v*P).
+- Documentation records how to override any of the named families with a
+  fontconfig alias, for users who prefer their own script fonts.
+
+## [1.8.0] - 2026-08
+
+### Added
+- `tidy` layout scale, one option covering every layout mode from the most
+  spacious to the most dense: `symmetric` (radical symmetrization) | `off` |
+  `low` (contour packing, strict leaf positions) | `medium` (packing with
+  cross-row tucking that never lets two leaves swap their left-right order) |
+  `high` (free tucking; leaf order kept per row only). Connector heights
+  adjust automatically: a small height budget (5% of the tree's height) is
+  spent on the levels whose branches spread widest, evening out branch
+  angles. Tidy never produces overlapping labels (collisions roll back).
+- `mirror` option: flips the finished layout horizontally for the
+  right-to-left tree convention of Arabic/Hebrew syntax (composes with
+  `direction`).
+- `hspacing` option: scales every horizontal gap in every layout mode — the
+  horizontal counterpart of `vheight`/connector height.
+- Pass-through empty nodes: a node labeled only `<>` renders as an invisible
+  joint with the connector running continuously through it, so a `<>` chain
+  aligns a shallow leaf with deeper leaves without a broken line.
+- Full CJK coverage in every font style: the family chains fall back to
+  Noto Sans/Serif/Mono CJK, so Hangul and simplified/traditional Han render
+  in all styles (the standalone Noto JP faces carry no Hangul).
+- Example gallery: Multilingual category (the same UD-PUD sentence in nine
+  languages, constituency derived mechanically from the dependency
+  annotation; the Arabic example demonstrates `mirror`), a Morphology
+  category, and per-figure tidy settings across the whole gallery.
+- CI on GitHub Actions (Ruby 3.2/3.4).
+
+### Changed
+- LSIF output records the layout settings a reader cannot recover from the
+  coordinates: `geometry.mirror`, and `tidy`, `mirror`, `direction` and
+  `horizontal_spacing` under `meta.source.params`.
+- The standalone `symmetrize` option and `-y` flag are deprecated aliases of
+  `tidy: symmetric`; `tidy_spacing` is a deprecated alias of `hspacing`.
+- `--direction` now owns the `-d` short flag (it had been auto-assigned to
+  `--hide-default-connectors`, so the documented `-d ltr` silently did
+  nothing). Every published short flag is now declared explicitly rather
+  than derived from the option set. One undocumented auto-assignment moved
+  as a result: `-e` was `--direction` in 1.7.0 and is `--version` here.
+- The gem no longer bundles font files (38MB that were never opened at
+  runtime since the Pango migration): fonts resolve by family name through
+  fontconfig. See README for the system font packages. The dead `--font`
+  CLI option (its value was never read) is gone.
+
+### Fixed
+- Boolean options left at their defaults are no longer misread as enabled
+  when the caller passes only a partial parameter set (e.g. `tidy: off`
+  rendered as `symmetric` in the web UI).
+
 ## [1.7.0] - 2026-08
 
 ### Changed

data/CITATION.cff

@@ -11,8 +11,8 @@ repository-code: "https://github.com/yohasebe/rsyntaxtree"
 # Concept DOI: always resolves to the latest archived version on Zenodo
 doi: "10.5281/zenodo.21916150"
 license: MIT
-version: 1.7.0
-date-released: "2026-08-13"
+version: 1.8.1
+date-released: 2026-08-15
 keywords:
   - linguistics
   - syntax tree

data/Dockerfile

@@ -7,16 +7,33 @@ RUN apk update && \
     apk add --no-cache linux-headers libxml2-dev make gcc libc-dev bash && \
     apk add --no-cache librsvg librsvg-dev pango-dev imagemagick imagemagick-dev xz-dev libbz2 && \
     apk add --no-cache gobject-introspection gobject-introspection-dev && \
-    apk add --no-cache -t .build-packages --no-cache build-base curl-dev wget gcompat
+    apk add --no-cache -t .build-packages --no-cache build-base curl-dev wget gcompat && \
+    apk add --no-cache font-noto font-noto-cjk font-noto-cjk-extra \
+        font-noto-arabic font-noto-naskh-arabic font-noto-hebrew \
+        font-noto-devanagari font-noto-thai font-noto-khmer
+
+# Noto Sans Math (pulled in by font-noto) claims the Arabic block but carries no
+# joining rules, and fontconfig ranks it above Noto Sans Arabic — Arabic then
+# renders as isolated letterforms. Keep the font, since trees use its
+# mathematical alphanumerics (the little v of vP), but drop Arabic from it.
+COPY dev/fontconfig/99-noto-math-no-arabic.conf /etc/fonts/conf.d/99-noto-math-no-arabic.conf
+
+# Emoji: the monochrome Noto Emoji, not Alpine's font-noto-emoji (which is the
+# colour NotoColorEmoji). Cairo does not rasterise its bitmap glyphs in this
+# pipeline, so emoji would silently fall back to whatever outline font happens
+# to cover them. Pinned to a google/fonts commit so the gallery stays stable.
+ARG NOTO_EMOJI_SHA=b979dba422e445492b0eb9951ac52ee0b4d648c3
+ARG NOTO_EMOJI_SHA256=de6c18832938afc99caf132b39d6a30a19bac7f2e812e28db2535b4608d27551
+RUN mkdir -p /usr/share/fonts/noto-emoji && \
+    wget -q -O /usr/share/fonts/noto-emoji/NotoEmoji-Regular.ttf \
+      "https://raw.githubusercontent.com/google/fonts/${NOTO_EMOJI_SHA}/ofl/notoemoji/NotoEmoji%5Bwght%5D.ttf" && \
+    echo "${NOTO_EMOJI_SHA256}  /usr/share/fonts/noto-emoji/NotoEmoji-Regular.ttf" | sha256sum -c -
 
 
 ADD Gemfile $WORKSPACE
 ADD rsyntaxtree.gemspec $WORKSPACE
 RUN bundle install -j4
 
-ADD fonts $WORKSPACE
-RUN mkdir -p /usr/share/fonts/yh
-COPY ./fonts/* /usr/share/fonts/yh/
 RUN fc-cache -fv
 
 ADD . $WORKSPACE

data/README.md

@@ -110,6 +110,23 @@ See [RSyntaxTree Example Gallery](https://yohasebe.github.io/rsyntaxtree/example
 
 <img src='https://github.com/yohasebe/rsyntaxtree/blob/master/img/sample.png?raw=true' width='600' />
 
+## System Fonts
+
+RSyntaxTree resolves fonts by family name through fontconfig (measurement via Pango, rendering via librsvg), so the fonts must be installed on the system that generates the images. Recommended:
+
+- Debian/Ubuntu: `apt install fonts-noto-core fonts-noto-cjk fonts-noto-color-emoji`
+- Alpine: `apk add font-noto font-noto-cjk font-noto-cjk-extra font-noto-emoji` (the `-extra` package carries Noto Serif CJK)
+- macOS: install [Noto Sans/Serif](https://fonts.google.com/noto) (and Noto Sans/Serif JP for CJK); otherwise the system falls back to available fonts
+
+Any script supported by an installed font renders correctly — the family chains fall back from Noto Sans/Serif to the JP and CJK variants, so Japanese, Chinese (simplified and traditional) and Korean are covered by the Noto CJK package. As of v1.8.0 the gem no longer bundles font files (they were not used at runtime).
+
+Scripts outside Latin and CJK need their own Noto package, or they render as tofu boxes. Since v1.8.0 the gem names these families explicitly (`Noto Sans Arabic`, `Noto Naskh Arabic`, `Noto Sans/Serif Hebrew`, `Devanagari`, `Thai`, `Khmer`) instead of leaving them to the system fallback, so install them to get the intended shapes:
+
+- Debian/Ubuntu: `apt install fonts-noto-core` already covers them; on minimal images add `fonts-noto` for the full set
+- Alpine: `apk add font-noto-arabic font-noto-naskh-arabic font-noto-hebrew font-noto-devanagari font-noto-thai font-noto-khmer`
+
+Emoji need the **monochrome** [Noto Emoji](https://fonts.google.com/noto/specimen/Noto+Emoji); colour emoji fonts (`NotoColorEmoji`, shipped by Alpine's `font-noto-emoji` and Debian's `fonts-noto-color-emoji`) are measured but not drawn by the librsvg/Cairo pipeline, so emoji then fall back to whatever outline font happens to cover them.
+
 ## Installation
 
 ```bash
@@ -156,9 +173,11 @@ Usage:
 | `-n, --fontstyle` | Font style: sans, serif, cjk, mono | `sans` |
 | `-s, --fontsize` | Font size: 8-26 | `16` |
 | `-c, --color` | Color mode: modern, traditional, off | `modern` |
-| `-y, --symmetrize` | Symmetrical tree: on, off | `off` |
 | `-p, --polyline` | Polyline connectors: on, off | `off` |
 | `-d, --direction` | Tree layout direction: ttb, ltr | `ttb` |
+| `--tidy` | Layout scale: off, symmetric, low, medium, high | `off` |
+| `--hspacing` | Horizontal spacing factor, all layout modes (0.5-3.0) | `1.0` |
+| `-m, --mirror` | Flip the tree horizontally (RTL convention): on, off | `off` |
 
 Run `rsyntaxtree -h` for the full list of options.
 
@@ -201,7 +220,7 @@ If you use RSyntaxTree in your research, please cite it. You can use the "Cite t
   title   = {RSyntaxTree: A graphical syntax tree image generator},
   url     = {https://yohasebe.com/rsyntaxtree},
   doi     = {10.5281/zenodo.21916150},
-  version = {1.7.0},
+  version = {1.8.0},
   year    = {2026}
 }
 ```

data/bin/rsyntaxtree

@@ -15,7 +15,6 @@ CONFIG_VALIDATORS = {
   format: ->(v) { /\A(png|jpg|gif|pdf|svg|lsif)\z/ =~ v.to_s ? nil : "must be png, jpg, gif, pdf, svg, or lsif" },
   leafstyle: ->(v) { /\A(auto|triangle|bar|nothing)\z/ =~ v.to_s ? nil : "must be auto, triangle, bar, or nothing" },
   fontstyle: ->(v) { /\A(sans|serif|cjk|mono)\z/ =~ v.to_s ? nil : "must be sans, serif, cjk, or mono" },
-  font: ->(v) { v.nil? || File.exist?(v) ? nil : "must be path to an existing ttf font" },
   fontsize: ->(v) { v.is_a?(Integer) && v >= 8 && v <= 26 ? nil : "must be in the range of 8-26" },
   linewidth: ->(v) { v.is_a?(Integer) && v >= 1 && v <= 5 ? nil : "must be in the range of 1-5" },
   vheight: ->(v) { v.is_a?(Numeric) && v >= 0.5 && v <= 5.0 ? nil : "must be in the range of 0.5-5.0" },
@@ -24,6 +23,10 @@ CONFIG_VALIDATORS = {
   transparent: ->(v) { /\A(on|off|true|false)\z/ =~ v.to_s ? nil : "must be on or off" },
   polyline: ->(v) { /\A(on|off|true|false)\z/ =~ v.to_s ? nil : "must be on or off" },
   hide_default_connectors: ->(v) { /\A(on|off|true|false)\z/ =~ v.to_s ? nil : "must be on or off" },
+  mirror: ->(v) { /\A(on|off|true|false)\z/ =~ v.to_s ? nil : "must be on or off" },
+  tidy: ->(v) { /\A(off|symmetric|low|medium|high|on|compact|true|false)\z/ =~ v.to_s ? nil : "must be off, symmetric, low, medium, or high" },
+  hspacing: ->(v) { v.is_a?(Numeric) && v >= 0.5 && v <= 3.0 ? nil : "must be in the range of 0.5-3.0" },
+  tidy_spacing: ->(v) { v.is_a?(Numeric) && v >= 0.5 && v <= 3.0 ? nil : "must be in the range of 0.5-3.0" },
   direction: ->(v) { /\A(ttb|ltr)\z/ =~ v.to_s ? nil : "must be ttb or ltr" }
 }.freeze
 
@@ -84,7 +87,7 @@ unless loaded[:errors].empty?
 end
 
 opts = Optimist.options do
-  version "RSyntaxTree #{RSyntaxTree::VERSION} (c) 2024 Yoichiro Hasebe"
+  version "RSyntaxTree #{RSyntaxTree::VERSION} (c) 2026 Yoichiro Hasebe"
   banner <<~BANNER
     RSyntaxTree, (linguistic) syntax tree generator written in Ruby.
 
@@ -96,21 +99,24 @@ opts = Optimist.options do
     where [options] are:
   BANNER
 
-  opt :outdir, "Output directory", default: "./"
-  opt :outfilename, "Output file base name", default: "syntree"
-  opt :format, "Output format: png, jpg, gif, pdf, svg, or lsif", default: "png"
-  opt :leafstyle, "visual style of tree leaves: auto, triangle, bar, or nothing", default: "auto"
-  opt :fontstyle, "Font style (available when ttf font is specified): sans, serif, cjk, mono", default: "sans"
-  opt :font, "Path to a ttf font used to generate tree (optional)", type: String
-  opt :fontsize, "Size: 8-26", default: 16
-  opt :linewidth, "Size: 1-5", default: 1
-  opt :vheight, "Connector Height: 0.5-5.0", default: 2.0
-  opt :color, "Color text and bars: modern, traditional, or off", default: "modern"
-  opt :symmetrize, "Generate radically symmetrical, balanced tree: on or off", default: "off"
-  opt :transparent, "Make background transparent: on or off", default: "off"
-  opt :polyline, "draw polyline connectors: on or off", default: "off"
-  opt :hide_default_connectors, "make default connectors transparent: on or off", default: "off"
-  opt :direction, "Tree layout direction: ttb (top-to-bottom) or ltr (left-to-right)", default: "ttb"
+  opt :outdir, "Output directory", default: "./", short: :o
+  opt :outfilename, "Output file base name", default: "syntree", short: :u
+  opt :format, "Output format: png, jpg, gif, pdf, svg, or lsif", default: "png", short: :f
+  opt :leafstyle, "visual style of tree leaves: auto, triangle, bar, or nothing", default: "auto", short: :l
+  opt :fontstyle, "Font style: sans, serif, cjk, mono", default: "sans", short: :n
+  opt :fontsize, "Size: 8-26", default: 16, short: :s
+  opt :linewidth, "Size: 1-5", default: 1, short: :i
+  opt :vheight, "Connector Height: 0.5-5.0", default: 2.0, short: :v
+  opt :color, "Color text and bars: modern, traditional, or off", default: "modern", short: :c
+  opt :symmetrize, "DEPRECATED alias of --tidy symmetric: on or off", default: "off", short: :y
+  opt :transparent, "Make background transparent: on or off", default: "off", short: :r
+  opt :polyline, "draw polyline connectors: on or off", default: "off", short: :p
+  opt :hide_default_connectors, "make default connectors transparent: on or off", default: "off", short: :none
+  opt :mirror, "flip the tree horizontally (RTL linguistics convention: first word at the right edge): on or off", default: "off"
+  opt :tidy, "tidy tree layout: off, symmetric (radical symmetrization), low (packed, strict leaf positions), medium (packed; leaves may overlap but never swap order), or high (packed; leaf order kept per row only)", default: "off", short: :none
+  opt :hspacing, "Horizontal spacing factor (counterpart of vheight): 0.5-3.0", default: 1.0, short: :none
+  opt :tidy_spacing, "DEPRECATED alias of --hspacing: 0.5-3.0", default: 1.0, short: :none
+  opt :direction, "Tree layout direction: ttb (top-to-bottom) or ltr (left-to-right)", default: "ttb", short: :d
   opt :help, "This is a custom help message", short: :h
 end
 
@@ -119,7 +125,6 @@ Optimist.die :direction, "must be ttb or ltr" unless /\A(ttb|ltr)\z/ =~ opts[:di
 Optimist.die :format, "must be png, pdf, svg, or lsif" unless /\A(png|jpg|gif|pdf|svg|lsif)\z/ =~ opts[:format]
 Optimist.die :leafstyle, "must be auto, triangle, bar, or nothing" unless /\A(auto|triangle|bar|nothing)\z/ =~ opts[:leafstyle]
 Optimist.die :fontstyle, "must be sans, serif, cjk, or mono" unless /\A(sans|serif|cjk|mono)\z/ =~ opts[:fontstyle]
-Optimist.die :font, "must be path to an existing ttf font" if opts[:font] && !File.exist?(opts[:font])
 Optimist.die :fontsize, "must be in the range of 8-26" unless opts[:fontsize] >= 8 && opts[:fontsize] <= 26
 Optimist.die :linewidth, "must be in the range of 1-5" unless opts[:linewidth] >= 1 && opts[:linewidth] <= 5
 Optimist.die :color, "must be either modern, traditional, or off" unless /\A(modern|traditional|on|off|true|false)\z/ =~ opts[:color]
@@ -128,6 +133,10 @@ Optimist.die :vheight, "must be in the range of 0.5-5.0" if opts[:vheight] < 0.5
 Optimist.die :transparent, "must be either on or off" unless /\A(on|off|true|false)\z/ =~ opts[:transparent]
 Optimist.die :polyline, "must be either on or off" unless /\A(on|off|true|false)\z/ =~ opts[:polyline]
 Optimist.die :hide_default_connectors, "must be either on or off" unless /\A(on|off|true|false)\z/ =~ opts[:hide_default_connectors]
+Optimist.die :mirror, "must be either on or off" unless /\A(on|off|true|false)\z/ =~ opts[:mirror]
+Optimist.die :tidy, "must be off, symmetric, low, medium, or high" unless /\A(off|symmetric|low|medium|high|on|compact|true|false)\z/ =~ opts[:tidy]
+Optimist.die :hspacing, "must be in the range of 0.5-3.0" if opts[:hspacing] < 0.5 || opts[:hspacing] > 3.0
+Optimist.die :tidy_spacing, "must be in the range of 0.5-3.0" if opts[:tidy_spacing] < 0.5 || opts[:tidy_spacing] > 3.0
 
 # Merge config file options with CLI options (CLI takes precedence)
 string_opts = {}
@@ -140,8 +149,8 @@ end
 # Then, apply CLI options (overrides config file)
 opts.each do |key, value|
   key_sym = key.to_sym
-  # Skip internal optimist keys and nil font
-  next if key.to_s.start_with?('_') || (key == :font && !value)
+  # Skip internal optimist keys
+  next if key.to_s.start_with?('_')
   # Only override if explicitly given on CLI or not in config
   if opts[:"#{key}_given"] || !file_config.key?(key_sym)
     string_opts[key_sym] = value