asciichem 0.24.0 → 0.25.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: d733aab290b1e54dfd0139d75a92888dfb8fc2af088544a07cc4395e523e583f
-  data.tar.gz: 5dfe21e949307366a6afbcc94bf2c52f9e9cfedb4a1f328996fbde3a20b5ec99
+  metadata.gz: 7748aa7fb152b3dad47ff42c2debe7335af35a2a36c21d2248ff4f5a5231c575
+  data.tar.gz: 4352b4fe40fc6998f9860d155e791d7cf2c4f3cd48f0184696346ba934adaa57
 SHA512:
-  metadata.gz: cdeb663f26df5189cd73df0d7c5f6a9ad3918d981d924ec08f1a781728415af474840de566a8d8f1075cb0cdc0d7086f41f92b80250efee6f71ebd11cdc62680
-  data.tar.gz: 371e88363eb2e143b2b8a1b3f1a3cbc339d3eb81d5bcd521fdc00d02fd90e6068c769864185198c8e35e5ae6e2fc95b0088885d760844f527118a50469eaa9fb
+  metadata.gz: 6a22a8e911ec6a04498285f949f79c1ea5e7e6870d464e3229c3e783e744d151f0506b5200dba58e4e06f23177983dd80b24d172c6d5528e960907da821db64a
+  data.tar.gz: 9d57bab57705518c6f2b40d28f40b0b62c20237d26b9daf20ae4d65bd9b60ad8497ea304c60c163878c412cc6cf61a3c99a6a9179b027bef527e524758b87085

data/CHANGELOG.md

@@ -3,6 +3,15 @@
 All notable changes to AsciiChem are documented here.
 This project follows [Semantic Versioning](https://semver.org/).
 
+## [0.25.0] - 2026-09-14
+
+### Added
+- CLI `cite` — resolve a substance and emit the dataset-type Relaton
+  bibitem XML (the citation track's user-facing entry point).
+- Cross-engine parsing benchmarks (`benchmarks/engines.rb`,
+  README with Ruby/TS/Python numbers) and the parsanol investigation
+  verdict (compat shim ~6x slower than parslet; not adopted).
+
 ## [0.24.0] - 2026-09-13
 
 ### Added
@@ -426,7 +435,8 @@ This project follows [Semantic Versioning](https://semver.org/).
   `version`.
 - Comprehensive RSpec suite with round-trip conformance.
 
-[Unreleased]: https://github.com/asciichem/asciichem-ruby/compare/v0.24.0...HEAD
+[Unreleased]: https://github.com/asciichem/asciichem-ruby/compare/v0.25.0...HEAD
+[0.25.0]: https://github.com/asciichem/asciichem-ruby/compare/v0.24.0...v0.25.0
 [0.24.0]: https://github.com/asciichem/asciichem-ruby/compare/v0.23.0...v0.24.0
 [0.23.0]: https://github.com/asciichem/asciichem-ruby/compare/v0.22.0...v0.23.0
 [0.22.0]: https://github.com/asciichem/asciichem-ruby/compare/v0.21.0...v0.22.0

data/benchmarks/README.md

@@ -0,0 +1,46 @@
+# Parsing benchmarks
+
+Shared workload (identical inputs in every implementation) so numbers
+are comparable across engines:
+
+```ruby
+WORKLOAD = ["H_2O", "Ca^2+", "SO_4^2-", "(R)-CH_3CH(OH)COOH",
+            "2H_2 + O_2 -> 2H_2O", "N_2 + 3H_2 <=>[Fe][400C] 2NH_3",
+            "C1-C-C-C-C-C1", "CH_3-CH_2-OH",
+            "^14C @name(\"carbon-14\") @cas(\"14104-86-4\")",
+            "A ->[heat] B ->[cool] C"]
+```
+
+| Engine | Batch (10 inputs) | Per input | Notes |
+|---|---|---|---|
+| Ruby (parslet), 3.4.8 arm64 | 29.1 ms | ~2.9 ms | `bundle exec ruby benchmarks/engines.rb` |
+| Ruby + parse+text | 35.3 ms | ~3.5 ms | round-trip adds the formatter |
+| TypeScript (peggy), Node 24 | 0.19 ms | ~19 µs | `npm run bench` (asciichem-ts) |
+| Python (RD), 3.10 | 3.94 ms | ~394 µs | `python benchmarks/engines.py` (asciichem-py) |
+
+The peggy engine is ~15x faster than parslet and ~20x faster than the
+Python recursive-descent parser on this workload — the grammar-port
+TS implementation did not trade away speed. Same machine (arm64),
+single-run medians; treat as order-of-magnitude comparison.
+
+## Parsanol investigation (2026-09-14)
+
+[Parsanol](https://github.com/parsanol/parsanol-ruby) (Ribose's
+parslet-alternative PEG library with a Rust native core) was evaluated
+as a drop-in speedup for the reference grammar:
+
+1. **Parslet-compat shim** (zero code change — re-parent the grammar
+   onto `Parsanol::Parslet::Parser`): the identical grammar runs
+   unchanged (10/10 workload inputs), but measures **~6x slower**
+   than parslet (12.2 s vs 2.05 s per 300x10 parses, Ruby 3.4.8,
+   arm64). The shim is a compatibility layer, not the fast path.
+2. **Native Parsanol DSL** (subset micro-benchmark): constructs run,
+   but boundary semantics differ from parslet on greedy-regex +
+   `maybe`/`repeat` interaction (`SO_4^2-` parses under parslet,
+   fails under Parsanol native). A full port would need per-rule
+   revalidation against the whole corpus with no measured win to
+   justify it yet.
+
+**Verdict: not adopted.** Revisit when Parsanol's native backend can
+be engaged for full grammars and shows measured wins on this
+workload; the shim path is a documented no.

data/benchmarks/engines.rb

@@ -0,0 +1,31 @@
+# frozen_string_literal: true
+
+# Cross-engine parsing benchmark (shared inputs across Ruby/TS/Python
+# so numbers are comparable). Measures full parse (+ Text round-trip
+# where cheap) over the canonical workload, reporting ops/sec and
+# µs/op. Run: bundle exec ruby benchmarks/engines.rb
+require "benchmark/ips"
+require "asciichem"
+
+WORKLOAD = [
+  "H_2O",
+  "Ca^2+",
+  "SO_4^2-",
+  "(R)-CH_3CH(OH)COOH",
+  "2H_2 + O_2 -> 2H_2O",
+  "N_2 + 3H_2 <=>[Fe][400C] 2NH_3",
+  "C1-C-C-C-C-C1",
+  "CH_3-CH_2-OH",
+  "^14C @name(\"carbon-14\") @cas(\"14104-86-4\")",
+  "A ->[heat] B ->[cool] C",
+].freeze
+
+Benchmark.ips do |x|
+  x.report("parse x10 (parslet)") do
+    WORKLOAD.each { |s| AsciiChem.parse(s) }
+  end
+  x.report("parse+text x10") do
+    WORKLOAD.each { |s| AsciiChem.parse(s).to_text }
+  end
+  x.compare!
+end

data/lib/asciichem/cli.rb

@@ -119,6 +119,33 @@ module AsciiChem
       exit 3
     end
 
+    desc "cite --cas X | --name X | ...", "Resolve a substance and emit a dataset-type Relaton bibitem (XML)"
+    method_option :cas, type: :string, desc: "CAS registry number"
+    method_option :name, type: :string, desc: "Substance name"
+    method_option :cid, type: :string, desc: "PubChem CID"
+    method_option :inchikey, type: :string, desc: "InChIKey"
+    method_option :smiles, type: :string, desc: "SMILES"
+    method_option :source, type: :string, default: "pubchem", desc: "Resolver source"
+    method_option :refresh, type: :boolean, default: false, desc: "Bypass the cache"
+    def cite
+      convention, value = %i[cas name cid inchikey smiles]
+                          .filter_map { |k| [k, options[k.to_s]] if options[k.to_s] }
+                          .first
+      raise AsciiChem::Error, "give one of --cas/--name/--cid/--inchikey/--smiles" unless value
+
+      convention = { cas: "cas", name: "name", cid: "pubchem-cid",
+                     inchikey: "inchikey", smiles: "smiles" }.fetch(convention)
+      substance = AsciiChem::Resolver[options[:source]].new.resolve(
+        value: value, convention: convention, refresh: options[:refresh]
+      )
+      raise AsciiChem::Error, "#{options[:source]} does not know #{value.inspect}" unless substance
+
+      puts AsciiChem::Citation.to_xml(substance)
+    rescue AsciiChem::Error => e
+      warn "Cite error: #{e.message}"
+      exit 4
+    end
+
     desc "validate -i INPUT", "Offline identifier validation"
     method_option :input, aliases: "-i", type: :string, required: true
     def validate

data/lib/asciichem/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module AsciiChem
-  VERSION = "0.24.0"
+  VERSION = "0.25.0"
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: asciichem
 version: !ruby/object:Gem::Version
-  version: 0.24.0
+  version: 0.25.0
 platform: ruby
 authors:
 - Ribose Inc.
@@ -172,8 +172,10 @@ files:
 - RELEASING.md
 - Rakefile
 - asciichem.gemspec
+- benchmarks/README.md
 - benchmarks/RESULTS.md
 - benchmarks/benchmark.rb
+- benchmarks/engines.rb
 - exe/asciichem
 - lib/asciichem.rb
 - lib/asciichem/citation.rb