parsanol 1.3.8 → 1.3.10

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: ca5f39af8b6ed42fb15609ae995687d58531d88b899a7c81fd708b2e36f9cf8d
-  data.tar.gz: 2a1d92d10d6f258ba0f79de6d6df22ffab5993ba8bc60f4ddfcbbc86a036546b
+  metadata.gz: 4db89a80339a628a73fff78b0c139b82378a3264e2009021ef2665fe40717731
+  data.tar.gz: f3be215e5a7c60837082916d36acba8443715206dcf3d5b875f5372c7c4ec985
 SHA512:
-  metadata.gz: bede99bb9de3cef6a3cb934c3405114bc082fd7e071d3ec320739b93ecedb73bc114d41452cacd9ef3337ca950047916b48ba3d3001f46accf813ec8e2338e3d
-  data.tar.gz: 7f29093ef0e2023dffbbb8a5bcffd0c8e59a99a247ca73361e349c62e4defdb2039afe31c0b5c29050074b93767dfd187931ec567051b9bf30f23577ab7b1fc3
+  metadata.gz: 9922b36fd81975232080e50a7d4f5b78604349be51a7812ec17d564a027d8f0152e9ec0e764fb57dfda2538cfb7247e3a6bd4d4c10feacdd795d7ffa907ed2ee
+  data.tar.gz: 9e7fe2260017d554dcb260c7f3583d31d2da2cdb4081ff049259290d63a65abece0722906982d1c125facd88316502f5d0e82b890e306a6b93d8afc24a9f856f

data/Cargo.lock

@@ -206,15 +206,15 @@ dependencies = [
 
 [[package]]
 name = "itoa"
-version = "1.0.17"
+version = "1.0.18"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "92ecc6618181def0457392ccd0ee51198e065e016d1d527a7ac1b6dc7c1f09d2"
+checksum = "8f42a60cbdf9a97f5d2305f08a87dc4e09308d1276d28c869c684d7777685682"
 
 [[package]]
 name = "js-sys"
-version = "0.3.91"
+version = "0.3.92"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "b49715b7073f385ba4bc528e5747d02e66cb39c6146efb66b781f131f0fb399c"
+checksum = "cc4c90f45aa2e6eacbe8645f77fdea542ac97a494bcd117a67df9ff4d611f995"
 dependencies = [
  "once_cell",
  "wasm-bindgen",
@@ -305,8 +305,8 @@ checksum = "9f7c3e4beb33f85d45ae3e3a1792185706c8e16d043238c593331cc7cd313b50"
 
 [[package]]
 name = "parsanol"
-version = "0.4.1"
-source = "git+https://github.com/parsanol/parsanol-rs?rev=3716de2#3716de22dc7e371e2dfb59bb28f443d0d1550b9e"
+version = "0.5.1"
+source = "git+https://github.com/parsanol/parsanol-rs?branch=main#6de2f6877b75c3d4ab2d73dd75cf32405e1f5505"
 dependencies = [
  "ahash",
  "getrandom 0.3.4",
@@ -322,8 +322,8 @@ dependencies = [
 
 [[package]]
 name = "parsanol-derive"
-version = "0.4.1"
-source = "git+https://github.com/parsanol/parsanol-rs?rev=3716de2#3716de22dc7e371e2dfb59bb28f443d0d1550b9e"
+version = "0.5.1"
+source = "git+https://github.com/parsanol/parsanol-rs?branch=main#6de2f6877b75c3d4ab2d73dd75cf32405e1f5505"
 dependencies = [
  "proc-macro2",
  "quote",
@@ -382,16 +382,16 @@ checksum = "f8dcc9c7d52a811697d2151c701e0d08956f92b0e24136cf4cf27b57a6a0d9bf"
 
 [[package]]
 name = "rb-sys"
-version = "0.9.124"
-source = "git+https://github.com/oxidize-rb/rb-sys.git?rev=b42b5fba0424fcc6778fed9a01e05215eaa53f85#b42b5fba0424fcc6778fed9a01e05215eaa53f85"
+version = "0.9.126"
+source = "git+https://github.com/oxidize-rb/rb-sys.git?rev=daa12b6521a0c442a705d7f9a929029119aab1d6#daa12b6521a0c442a705d7f9a929029119aab1d6"
 dependencies = [
  "rb-sys-build",
 ]
 
 [[package]]
 name = "rb-sys-build"
-version = "0.9.124"
-source = "git+https://github.com/oxidize-rb/rb-sys.git?rev=b42b5fba0424fcc6778fed9a01e05215eaa53f85#b42b5fba0424fcc6778fed9a01e05215eaa53f85"
+version = "0.9.126"
+source = "git+https://github.com/oxidize-rb/rb-sys.git?rev=daa12b6521a0c442a705d7f9a929029119aab1d6#daa12b6521a0c442a705d7f9a929029119aab1d6"
 dependencies = [
  "bindgen",
  "lazy_static",
@@ -439,9 +439,9 @@ checksum = "dc897dd8d9e8bd1ed8cdad82b5966c3e0ecae09fb1907d58efaa013543185d0a"
 
 [[package]]
 name = "rustc-hash"
-version = "2.1.1"
+version = "2.1.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "357703d41365b4b27c590e3ed91eabb1b663f07c4c084095e60cbed4362dff0d"
+checksum = "94300abf3f1ae2e2b8ffb7b58043de3d399c73fa6f4b73826402a5c457614dbe"
 
 [[package]]
 name = "rustversion"
@@ -565,9 +565,9 @@ dependencies = [
 
 [[package]]
 name = "wasm-bindgen"
-version = "0.2.114"
+version = "0.2.115"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "6532f9a5c1ece3798cb1c2cfdba640b9b3ba884f5db45973a6f442510a87d38e"
+checksum = "6523d69017b7633e396a89c5efab138161ed5aafcbc8d3e5c5a42ae38f50495a"
 dependencies = [
  "cfg-if",
  "once_cell",
@@ -578,9 +578,9 @@ dependencies = [
 
 [[package]]
 name = "wasm-bindgen-macro"
-version = "0.2.114"
+version = "0.2.115"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "18a2d50fcf105fb33bb15f00e7a77b772945a2ee45dcf454961fd843e74c18e6"
+checksum = "4e3a6c758eb2f701ed3d052ff5737f5bfe6614326ea7f3bbac7156192dc32e67"
 dependencies = [
  "quote",
  "wasm-bindgen-macro-support",
@@ -588,9 +588,9 @@ dependencies = [
 
 [[package]]
 name = "wasm-bindgen-macro-support"
-version = "0.2.114"
+version = "0.2.115"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "03ce4caeaac547cdf713d280eda22a730824dd11e6b8c3ca9e42247b25c631e3"
+checksum = "921de2737904886b52bcbb237301552d05969a6f9c40d261eb0533c8b055fedf"
 dependencies = [
  "bumpalo",
  "proc-macro2",
@@ -601,9 +601,9 @@ dependencies = [
 
 [[package]]
 name = "wasm-bindgen-shared"
-version = "0.2.114"
+version = "0.2.115"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "75a326b8c223ee17883a4251907455a2431acc2791c98c26279376490c378c16"
+checksum = "a93e946af942b58934c604527337bad9ae33ba1d5c6900bbb41c2c07c2364a93"
 dependencies = [
  "unicode-ident",
 ]
@@ -738,18 +738,18 @@ dependencies = [
 
 [[package]]
 name = "zerocopy"
-version = "0.8.42"
+version = "0.8.48"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "f2578b716f8a7a858b7f02d5bd870c14bf4ddbbcf3a4c05414ba6503640505e3"
+checksum = "eed437bf9d6692032087e337407a86f04cd8d6a16a37199ed57949d415bd68e9"
 dependencies = [
  "zerocopy-derive",
 ]
 
 [[package]]
 name = "zerocopy-derive"
-version = "0.8.42"
+version = "0.8.48"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "7e6cc098ea4d3bd6246687de65af3f920c430e236bee1e3bf2e441463f08a02f"
+checksum = "70e3cd084b1788766f53af483dd21f93881ff30d7320490ec3ef7526d203bad4"
 dependencies = [
  "proc-macro2",
  "quote",

data/Cargo.toml

@@ -12,4 +12,4 @@ debug = true
 [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" }
+rb-sys = { git = "https://github.com/oxidize-rb/rb-sys.git", rev = "daa12b6521a0c442a705d7f9a929029119aab1d6" }

data/ext/parsanol_native/Cargo.toml

@@ -28,7 +28,7 @@ rb-sys = { version = "0.9.124", features = ["global-allocator"] }
 magnus = { version = "0.9" }
 
 # parsanol parser library (from git for latest features)
-parsanol = { git = "https://github.com/parsanol/parsanol-rs", rev = "3716de2", features = ["ruby"] }
+parsanol = { git = "https://github.com/parsanol/parsanol-rs", branch = "main", features = ["ruby"] }
 
 # Logging
 log = "0.4"

data/lib/parsanol/grammar_builder.rb

@@ -115,7 +115,7 @@ module Parsanol
     # Convert to JSON for native parser
     #
     # @return [String] JSON representation
-    def to_json(*_args)
+    def to_json(*)
       build.to_json
     end
 

data/lib/parsanol/native/batch_decoder.rb

@@ -57,9 +57,8 @@ module Parsanol
         #   pre-decoded Ruby value from _parse_raw
         # @param input [String] Original input string (for Slice references)
         # @param slice_class [Class] The Slice class to use
-        # @param grammar_atom [Parsanol::Atoms::Base] The grammar atom (unused, kept for API compat)
         # @return [Object] Transformed Ruby AST
-        def decode_and_flatten(data, input, slice_class, _grammar_atom)
+        def decode_and_flatten(data, input, slice_class)
           # Check if data is batch data (flat u64 array) or already a Ruby value
           if data.is_a?(Integer) || (data.is_a?(Array) && data.first.is_a?(Integer))
             # Batch data (flat u64 array) - decode first, then transform

data/lib/parsanol/native/transformer.rb

@@ -323,9 +323,26 @@ module Parsanol
               all_items_are_hashes = non_hash_items.empty?
 
               if all_items_are_hashes
-                # Merge all inner hashes into merged_hash
-                item.each do |sub_item|
-                  merged_hash.merge!(sub_item) if sub_item.is_a?(Hash)
+                # Check if merging would overwrite existing keys in merged_hash.
+                # If so, this is a repetition pattern (item >> (sep >> item).repeat)
+                # and should be kept as array, not merged.
+                # Example: merged_hash={namedTypeOrRename: A}, array=[{namedTypeOrRename: B}]
+                # → should produce [{namedTypeOrRename: A}, {namedTypeOrRename: B}]
+                existing_keys = merged_hash.keys
+                shares_keys = item.any? do |sub_item|
+                  sub_item.is_a?(Hash) && sub_item.keys.intersect?(existing_keys)
+                end
+
+                if shares_keys
+                  has_non_empty_array = true
+                  item.each do |sub_item|
+                    hash_count += 1 if sub_item.is_a?(Hash)
+                  end
+                  total_items += 1
+                else
+                  item.each do |sub_item|
+                    merged_hash.merge!(sub_item) if sub_item.is_a?(Hash)
+                  end
                 end
               else
                 # Non-empty repetition with non-hash items - mark that we should keep as array

data/lib/parsanol/native/types.rb

@@ -25,18 +25,5 @@ module Parsanol
       EMPTY_ARRAY = [].freeze
       EMPTY_HASH = {}.freeze
     end
-
-    # Symbol cache to avoid repeated string-to-symbol conversions
-    # This is a class variable to share across all transformations
-    @@symbol_cache = {}
-
-    # Convert string key to symbol with caching
-    # @param key [String, Symbol] The key to convert
-    # @return [Symbol] The symbol version of the key
-    def self.cached_symbol(key)
-      return key if key.is_a?(Symbol)
-
-      @@symbol_cache[key] ||= key.to_sym
-    end
   end
 end

data/lib/parsanol/native.rb

@@ -10,8 +10,6 @@ require "parsanol/native/batch_decoder"
 
 module Parsanol
   module Native
-    VERSION = "0.1.0"
-
     class << self
       # Check if native extension is available
       def available?
@@ -41,20 +39,38 @@ module Parsanol
         raise LoadError, "Native parser not available" unless available?
 
         # Handle both grammar atoms and pre-serialized JSON strings
-        if grammar.is_a?(String)
-          grammar_json = grammar
-          grammar_atom = nil
-        else
-          grammar_json = Parser.serialize_grammar(grammar)
-          grammar_atom = grammar
-        end
+        grammar_json = if grammar.is_a?(String)
+                         grammar
+                       else
+                         Parser.serialize_grammar(grammar)
+                       end
 
         # Use _parse_raw which returns properly tagged Ruby arrays via transform_ast.
         # The batch format doesn't preserve :repetition/:sequence tags, so we use
         # the direct FFI path. Apply the Ruby transformer to handle tags correctly.
         raw_ast = _parse_raw(grammar_json, input)
-        BatchDecoder.decode_and_flatten(raw_ast, input, Parsanol::Slice,
-                                        grammar_atom)
+        BatchDecoder.decode_and_flatten(raw_ast, input, Parsanol::Slice)
+      end
+
+      # Memory-bounded parsing without packrat cache.
+      #
+      # This creates a fresh arena and empty cache per call, bounding memory
+      # to AST size rather than input × atoms. Use for large files.
+      #
+      # @param grammar [Parsanol::Atoms::Base] Ruby grammar definition
+      # @param input [String] Input string to parse
+      # @return [Hash, Array, Parsanol::Slice] Transformed AST
+      def parse_fresh(grammar, input)
+        raise LoadError, "Native parser not available" unless available?
+
+        grammar_json = if grammar.is_a?(String)
+                         grammar
+                       else
+                         Parser.serialize_grammar(grammar)
+                       end
+
+        raw_ast = _parse_fresh_raw(grammar_json, input)
+        BatchDecoder.decode_and_flatten(raw_ast, input, Parsanol::Slice)
       end
 
       # Parse and return RAW AST without transformation.
@@ -166,13 +182,6 @@ module Parsanol
         end
         stats
       end
-
-      private
-
-      # Get the Slice class
-      def get_slice_class
-        Parsanol::Slice
-      end
     end
   end
 end

data/lib/parsanol/options/zero_copy.rb

@@ -89,11 +89,10 @@ module Parsanol
     # Parse input and return direct Ruby objects (no serialization)
     #
     # @param input [String] The input string to parse
-    # @param options [Hash] Parse options (ignored for zero-copy)
     # @return [Object] Direct Ruby object (type depends on grammar)
     # @raise [LoadError] If native extension not available
     # @raise [Parsanol::ParseFailed] If parsing fails
-    def parse(input, _options = {})
+    def parse(input)
       unless Parsanol::Native.available?
         raise LoadError,
               "ZeroCopy mode requires native extension for direct FFI object construction. " \

data/lib/parsanol/slice.rb

@@ -67,6 +67,10 @@ module Parsanol
 
     alias length size
 
+    def empty?
+      content.empty?
+    end
+
     def +(other)
       self.class.new(@byte_position, content + other.to_s, @input)
     end
@@ -110,7 +114,7 @@ module Parsanol
       as_json.to_json(*)
     end
 
-    def as_json(_options = {})
+    def as_json
       result = { "value" => content, "offset" => offset, "length" => length }
       if @input
         line, column = line_and_column

data/lib/parsanol/source/line_cache.rb

@@ -97,13 +97,6 @@ module Parsanol
           return hi if hi <= lo
         end
       end
-
-      # Legacy method name for backward compatibility
-      alias find_mid midpoint_index
-      alias lbound lower_bound_index
     end
-
-    # Legacy constant name for backward compatibility
-    RangeSearch = IntervalLookup
   end
 end

data/lib/parsanol/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module Parsanol
-  VERSION = "1.3.8"
+  VERSION = "1.3.10"
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: parsanol
 version: !ruby/object:Gem::Version
-  version: 1.3.8
+  version: 1.3.10
 platform: ruby
 authors:
 - Ribose Inc.