parsanol 1.2.2 → 1.3.3

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 4ff890cbd6143c5d47de4fb8f94610e6ffade56795275c483c0544ebc41bb0c4
-  data.tar.gz: 34697398d4a0e29a192d216a6936a2e37cb1f63d3468da5d94d5948becc5fb38
+  metadata.gz: bac63e41077cf9eed82a69de397d2248e532e09f5b26f149b2af88daed9b669c
+  data.tar.gz: 777066f81425836b34c629c0a3ef53b2297cfb4a2f963925be699a515f5d0751
 SHA512:
-  metadata.gz: ddbeb95ac05c7b26bcdc51c6fde845bffd4bb53536427e555cafff0d3b6b4ce8ffe9f1fc6a81e67a1c02641c06b42086d40e204430c34b53e37507aab9c4d5db
-  data.tar.gz: 7c5bcab451d43652465fd5980e1676bd93a1a2299a24f6546314758427039ee743826e43eca1ce8d4ea19c9cb1bceb68d5c8d81655392478727a169bc74f3b9f
+  metadata.gz: dd2fc966df72d3422c489d9e588260e54c298ea694ae96e0e3bf178ecc979b22e541593dfe8011d3cd9e1857625097b382cdfcfe5f4c65a9cf10a1372704ed0a
+  data.tar.gz: 58e95adb43e19330469176920fc8eb05f0b5f79b074552ae3d54805c40fbf324cf998e49ca4b5b73bc1ec65e3e0aab47472f8fafb7a6e3567ea8948c95eae539

data/Cargo.lock

@@ -38,16 +38,14 @@ checksum = "7f202df86484c868dbad7eaa557ef785d5c66295e41b460ef922eca0723b842c"
 
 [[package]]
 name = "bindgen"
-version = "0.69.5"
+version = "0.72.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "271383c67ccabffb7381723dea0672a673f292304fcb45c01cc648c7a8d58088"
+checksum = "993776b509cfb49c750f11b8f07a46fa23e0a1386ffc01fb1e7d343efc387895"
 dependencies = [
  "bitflags",
  "cexpr",
  "clang-sys",
  "itertools",
- "lazy_static",
- "lazycell",
  "proc-macro2",
  "quote",
  "regex",
@@ -125,9 +123,11 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "899def5c37c4fd7b2664648c28120ecec138e4d395b459e5ca34f9cce2dd77fd"
 dependencies = [
  "cfg-if",
+ "js-sys",
  "libc",
  "r-efi 5.3.0",
  "wasip2",
+ "wasm-bindgen",
 ]
 
 [[package]]
@@ -197,9 +197,9 @@ dependencies = [
 
 [[package]]
 name = "itertools"
-version = "0.12.1"
+version = "0.13.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "ba291022dbbd398a455acf126c1e341954079855bc60dfdda641363bd6922569"
+checksum = "413ee7dfc52ee1a4949ceeb7dbc8a33f2d6c088194d9f922fb8318faf1f01186"
 dependencies = [
  "either",
 ]
@@ -226,12 +226,6 @@ version = "1.5.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "bbd2bcb4c963f2ddae06a2efc7e9f3591312473c50c6685e1f298068316e66fe"
 
-[[package]]
-name = "lazycell"
-version = "1.3.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "830d08ce1d1d941e6b30645f1a0eb5643013d835ce3779a5fc208261dbe10f55"
-
 [[package]]
 name = "leb128fmt"
 version = "0.1.0"
@@ -240,9 +234,9 @@ checksum = "09edd9e8b54e49e587e4f6295a7d29c3ea94d469cb40ab8ca70b288248a81db2"
 
 [[package]]
 name = "libc"
-version = "0.2.182"
+version = "0.2.183"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "6800badb6cb2082ffd7b6a67e6125bb39f18782f793520caee8cb8846be06112"
+checksum = "b5b646652bf6661599e1da8901b3b9522896f01e736bad5f723fe7a3a27f899d"
 
 [[package]]
 name = "libloading"
@@ -262,9 +256,8 @@ checksum = "5e5032e24019045c762d3c0f28f5b6b8bbf38563a65908389bf7978758920897"
 
 [[package]]
 name = "magnus"
-version = "0.8.2"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "3b36a5b126bbe97eb0d02d07acfeb327036c6319fd816139a49824a83b7f9012"
+version = "0.9.0"
+source = "git+https://github.com/matsadler/magnus?rev=4e46772#4e46772050e47cd6cd988fa935263cc5c583e388"
 dependencies = [
  "magnus-macros",
  "rb-sys",
@@ -274,9 +267,8 @@ dependencies = [
 
 [[package]]
 name = "magnus-macros"
-version = "0.8.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "47607461fd8e1513cb4f2076c197d8092d921a1ea75bd08af97398f593751892"
+version = "0.9.0"
+source = "git+https://github.com/matsadler/magnus?rev=4e46772#4e46772050e47cd6cd988fa935263cc5c583e388"
 dependencies = [
  "proc-macro2",
  "quote",
@@ -307,23 +299,22 @@ dependencies = [
 
 [[package]]
 name = "once_cell"
-version = "1.21.3"
+version = "1.21.4"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "42f5e15c9953c5e4ccceeb2e7382a716482c34515315f7b03532b8b4e8393d2d"
+checksum = "9f7c3e4beb33f85d45ae3e3a1792185706c8e16d043238c593331cc7cd313b50"
 
 [[package]]
 name = "parsanol"
-version = "0.3.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "40e84f8cdc9f85960871f57d5fff33cf9e03deae0fd7f87b1f9655f35451fdf7"
+version = "0.4.1"
+source = "git+https://github.com/parsanol/parsanol-rs?rev=4667017#46670172240420221089cb4da6eaecadb23a0015"
 dependencies = [
  "ahash",
+ "getrandom 0.3.4",
  "getrandom 0.4.2",
  "hashbrown 0.16.1",
  "magnus",
  "memchr",
  "parsanol-derive",
- "rb-sys",
  "regex",
  "serde",
  "serde_json",
@@ -331,9 +322,8 @@ dependencies = [
 
 [[package]]
 name = "parsanol-derive"
-version = "0.3.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "bbd12999fd4452b4713c3d32ca200de0894da2636a215ed54e83c42a553c1aae"
+version = "0.4.1"
+source = "git+https://github.com/parsanol/parsanol-rs?rev=4667017#46670172240420221089cb4da6eaecadb23a0015"
 dependencies = [
  "proc-macro2",
  "quote",
@@ -371,9 +361,9 @@ dependencies = [
 
 [[package]]
 name = "quote"
-version = "1.0.44"
+version = "1.0.45"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "21b2ebcf727b7760c461f091f9f0f539b77b8e87f2fd88131e7f1b433b3cece4"
+checksum = "41f2619966050689382d2b44f664f4bc593e129785a36d6ee376ddf37259b924"
 dependencies = [
  "proc-macro2",
 ]
@@ -393,8 +383,7 @@ checksum = "f8dcc9c7d52a811697d2151c701e0d08956f92b0e24136cf4cf27b57a6a0d9bf"
 [[package]]
 name = "rb-sys"
 version = "0.9.124"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "c85c4188462601e2aa1469def389c17228566f82ea72f137ed096f21591bc489"
+source = "git+https://github.com/oxidize-rb/rb-sys.git?rev=b42b5fba0424fcc6778fed9a01e05215eaa53f85#b42b5fba0424fcc6778fed9a01e05215eaa53f85"
 dependencies = [
  "rb-sys-build",
 ]
@@ -402,8 +391,7 @@ dependencies = [
 [[package]]
 name = "rb-sys-build"
 version = "0.9.124"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "568068db4102230882e6d4ae8de6632e224ca75fe5970f6e026a04e91ed635d3"
+source = "git+https://github.com/oxidize-rb/rb-sys.git?rev=b42b5fba0424fcc6778fed9a01e05215eaa53f85#b42b5fba0424fcc6778fed9a01e05215eaa53f85"
 dependencies = [
  "bindgen",
  "lazy_static",
@@ -451,9 +439,9 @@ checksum = "dc897dd8d9e8bd1ed8cdad82b5966c3e0ecae09fb1907d58efaa013543185d0a"
 
 [[package]]
 name = "rustc-hash"
-version = "1.1.0"
+version = "2.1.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "08d43f7aa6b08d49f382cde6a7982047c3426db949b1424bc4b7ec9ae12c6ce2"
+checksum = "357703d41365b4b27c590e3ed91eabb1b663f07c4c084095e60cbed4362dff0d"
 
 [[package]]
 name = "rustversion"
@@ -750,18 +738,18 @@ dependencies = [
 
 [[package]]
 name = "zerocopy"
-version = "0.8.40"
+version = "0.8.42"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "a789c6e490b576db9f7e6b6d661bcc9799f7c0ac8352f56ea20193b2681532e5"
+checksum = "f2578b716f8a7a858b7f02d5bd870c14bf4ddbbcf3a4c05414ba6503640505e3"
 dependencies = [
  "zerocopy-derive",
 ]
 
 [[package]]
 name = "zerocopy-derive"
-version = "0.8.40"
+version = "0.8.42"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "f65c489a7071a749c849713807783f70672b28094011623e200cb86dcb835953"
+checksum = "7e6cc098ea4d3bd6246687de65af3f920c430e236bee1e3bf2e441463f08a02f"
 dependencies = [
  "proc-macro2",
  "quote",

data/Cargo.toml

@@ -4,6 +4,12 @@ members = ["ext/parsanol_native"]
 
 [profile.release]
 opt-level = 3
-lto = "thin"
+lto = "off"
 codegen-units = 1
-debug = true  # Enable debug info for better stack traces
+debug = true
+
+# Patches for Ruby 4.0 support (not yet on crates.io)
+[patch.crates-io]
+magnus = { git = "https://github.com/matsadler/magnus", rev = "4e46772" }
+magnus-macros = { git = "https://github.com/matsadler/magnus", rev = "4e46772" }
+rb-sys = { git = "https://github.com/oxidize-rb/rb-sys.git", rev = "b42b5fba0424fcc6778fed9a01e05215eaa53f85" }

data/HISTORY.txt

@@ -1,3 +1,33 @@
+== Parsanol 1.3.0 (unreleased)
+
+Breaking changes:
+
+* Simplified API: Single `parse()` method with lazy line/column
+* Removed deprecated methods: `parse_parslet`, `parse_parslet_with_positions`,
+  `parse_with_transform`, `parse_to_objects`, `parse_raw`
+
+New features:
+
+* Lazy line/column computation in `Slice#line_and_column` - computed only when accessed
+* `BatchDecoder` module for efficient batch AST processing
+* Grammar accepts Ruby atoms directly - no JSON serialization step needed
+
+Bug fixes:
+
+* Fixed grammar cache cycle detection to prevent stack overflow on recursive grammars
+* Fixed wrapper vs repetition pattern detection in `AstTransformer`:
+  - Same inner keys → Repetition pattern (keep as array)
+  - Different inner keys → Wrapper pattern (merge inner hashes)
+* Correct entity extraction for grammars with multiple declarations
+
+== Parsanol 1.2.2 (2026-03-07)
+
+Syncs with parsanol-rs 0.3.0:
+
+* Full FFI support for capture, scope, and dynamic atoms
+* Native extension performance for all new features
+* BuilderCallbacks module for streaming parsing
+
 == Parsanol 1.2.1 (2026-03-07)
 
 Bug fix:
@@ -34,12 +64,12 @@ Runtime-determined parsing via FFI callbacks:
 
 === Native Extension Updates
 
-* Updated to parsanol-rs 0.2.0
+* Updated to parsanol-rs 0.3.0
 * New backend abstraction (Packrat, Bytecode, Auto)
 * Streaming parser with capture extraction
 * Performance improvements
 
-== Parsanol 1.1.0 (2025-03-15)
+== Parsanol 1.1.0 (2026-03-05)
 
 Position information is now returned by default:
 
@@ -54,7 +84,7 @@ Performance improvements:
 * ZeroCopy API for direct FFI object construction
 * Parallel batch parsing with `Parsanol::Parallel`
 
-== Parsanol 1.0.0 (2025-03-02)
+== Parsanol 1.0.0 (2026-03-03)
 
 Initial release of Parsanol, a high-performance PEG parser library for Ruby.
 

data/README.adoc

@@ -21,7 +21,7 @@ While maintaining full API compatibility with Parslet, Parsanol features a compl
 
 * <<basic-parsing,PEG-based Parser Construction>> - Declarative grammar definition
 * <<error-reporting,Detailed Error Reporting>> - Precise failure location and context
-* <<native-extension,Rust Native Extension>> - Up to 29x faster parsing
+* <<native-extension,Rust Native Extension>> - **Up to 1300x faster parsing**
 * <<slice-support,Slice Support>> - Source position preservation for linters and IDEs
 * <<transformation,Tree Transformation>> - Pattern-based AST construction
 * <<streaming-builder,Streaming Builder API>> - Single-pass parsing with callbacks
@@ -29,6 +29,7 @@ While maintaining full API compatibility with Parslet, Parsanol features a compl
 * <<infix-expressions,Infix Expression Parsing>> - Built-in operator precedence support
 * <<security-features,Security Features>> - Input size and recursion limits
 * <<debug-tools,Debug Tools>> - Tracing and grammar visualization
+* <<benchmarking,Benchmarking>> - Built-in performance testing tools
 
 == Installation
 
@@ -53,6 +54,23 @@ Or install it yourself as:
 gem install parsanol
 ----
 
+== Examples
+
+The repository includes several example files demonstrating different use cases:
+
+* link:examples/benchmark_examples.rb[] - Basic performance benchmarks
+* link:examples/benchmark_full.rb[] - Comprehensive benchmark suite
+* link:examples/parsing_modes.rb[] - Demonstrates all parsing modes
+* link:examples/parslet_migration.rb[] - Migration guide from Parslet
+
+[source,ruby]
+----
+# Run examples
+bundle exec ruby examples/benchmark_examples.rb
+bundle exec ruby examples/parsing_modes.rb
+bundle exec ruby examples/parslet_migration.rb
+----
+
 == Usage
 
 [[basic-parsing]]
@@ -103,6 +121,23 @@ ast = MyTransform.new.apply(parse_tree)
 
 [[native-extension]]
 === Native Extension
+
+The Rust native extension provides significant performance improvements over pure Ruby parsing:
+
+[cols="2,1,1,1"]
+|===
+| Pattern Type | Ruby (i/s) | Native (i/s) | Speedup
+
+| Simple string match | ~575 | ~775,000 | **1,340x**
+| Sequence (3 parts) | ~580 | ~530,000 | **910x**
+| Named capture | ~575 | ~510,000 | **880x**
+| Repetition (10x digits) | ~560 | ~740,000 | **1,310x**
+| Alternative (3 options) | ~575 | ~720,000 | **1,250x**
+| Calculator expression | ~570 | ~180,000 | **315x**
+| Repetition with name | ~575 | ~125,000 | **220x**
+| Repetition (20x) | ~560 | ~720,000 | **1,280x**
+|===
+
 For maximum performance, compile the Rust native extension:
 
 [source,shell]
@@ -114,6 +149,13 @@ curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh
 bundle exec rake compile
 ----
 
+Run your own benchmarks with:
+
+[source,ruby]
+----
+bundle exec ruby examples/benchmark_examples.rb
+----
+
 [[slice-support]]
 === Slice Support
 
@@ -247,9 +289,9 @@ parser.parse('123')  # Works exactly the same
 | `sequence(:x)` | ✅ | Match array of values
 | `subtree(:x)` | ✅ | Match any subtree
 | `Parslet::Slice` | ✅ | Parsanol::Slice compatible
-| `.capture(:name)` | ✅ | Named capture extraction (NEW in 1.1.0)
-| `scope { }` | ✅ | Isolated capture context (NEW in 1.1.0)
-| `dynamic { \|ctx\| }` | ✅ | Runtime-determined parsing (NEW in 1.1.0)
+| `.capture(:name)` | ✅ | Named capture extraction (NEW in 1.2.0)
+| `scope { }` | ✅ | Isolated capture context (NEW in 1.2.0)
+| `dynamic { \|ctx\| }` | ✅ | Runtime-determined parsing (NEW in 1.2.0)
 |===
 
 NOTE: The new capture, scope, and dynamic atoms provide powerful extraction and context-sensitive parsing capabilities. See the <<captures,Captures>> section for details.
@@ -475,7 +517,7 @@ For more details on backend selection and grammar analysis, see the https://pars
 [[captures]]
 == Captures, Scopes, and Dynamic Atoms
 
-Parsanol 1.1.0 introduces powerful new features for extracting and managing parsed data.
+Parsanol 1.2.0 introduces powerful new features for extracting and managing parsed data.
 
 [[capture-atoms]]
 === Capture Atoms
@@ -789,12 +831,64 @@ ruby -I lib -e "require 'parsanol'; puts Parsanol::Native.available?"
 
 [source,shell]
 ----
-# Quick benchmarks
-bundle exec rake benchmark
+# Quick benchmarks (examples provided in the repository)
+bundle exec ruby examples/benchmark_examples.rb
+
+# Full benchmark suite
+bundle exec ruby examples/benchmark_full.rb
+
+# Compare parsing modes
+bundle exec ruby examples/parsing_modes.rb
+
+# Parslet migration examples
+bundle exec ruby examples/parslet_migration.rb
+----
+
+[[benchmarking]]
+== Benchmarking Your Own Code
 
-# Comprehensive benchmark suite
-bundle exec rake benchmark:all
+Parsanol includes built-in benchmarking tools to measure performance:
+
+[source,ruby]
 ----
+require 'parsanol'
+require 'benchmark/ips'
+
+# Your grammar
+grammar = Parsanol.str("hello").as(:greeting)
+json = Parsanol::Native.serialize_grammar(grammar)
+
+# Benchmark
+Benchmark.ips do |x|
+  x.config(warmup: 5, time: 3)
+
+  x.report("Ruby mode") { grammar.parse("hello", mode: :ruby) }
+  x.report("Native mode") { Parsanol::Native.parse(json, "hello") }
+
+  x.compare!
+end
+----
+
+=== Performance Factors
+
+The actual speedup depends on several factors:
+
+1. **Grammar complexity** - More complex grammars have more transformation overhead
+2. **Named captures** - More named captures mean more hash construction
+3. **Repetition patterns** - Named repetitions have more overhead than unnamed
+4. **Input size** - Larger inputs benefit more from native parsing
+
+[cols="1,2,2"]
+|===
+| Pattern | Speedup | Reason for Difference
+
+| Simple strings | ~1,300x | Minimal transformation
+| Sequences | ~900x | String joining overhead
+| Alternatives | ~1,250x | Fast path in Rust
+| Repetitions (unnamed) | ~1,300x | Minimal transformation
+| Repetitions (named) | ~220x | Array of hashes construction
+| Complex expressions | ~315x | More grammar elements
+|===
 
 == License
 

data/ext/parsanol_native/Cargo.toml

@@ -20,16 +20,19 @@ rust-version = "1.75"
 crate-type = ["cdylib"]
 
 [dependencies]
-# rb-sys for Ruby C API - with link-ruby to link at compile time
+# rb-sys for Ruby C API - WITHOUT link-ruby for dynamic extension
 # On Windows ARM64, we need to build from source since pre-built binaries aren't available
-rb-sys = { version = "0.9.124", features = ["link-ruby", "global-allocator"] }
+rb-sys = { version = "0.9.124", features = ["global-allocator"] }
 
-# magnus for Ruby bindings (0.8 for Ruby 3.1 support)
-magnus = "0.8"
+# magnus for Ruby bindings (from crates.io, patched locally for Ruby 4.0 support)
+magnus = { version = "0.9" }
 
-# parsanol parser library
-parsanol = { version = "0.3", features = ["ruby"] }
+# parsanol parser library (from git for latest features)
+parsanol = { git = "https://github.com/parsanol/parsanol-rs", rev = "4667017", features = ["ruby"] }
 
 # Logging
 log = "0.4"
 
+[profile.release]
+lto = "off"
+