Merge pull request #3085 from ruby/claude/jruby-pr-3083-null-issue-0s30d5

Handle the NULL parser in the WebAssembly shim

Author: soutaro

lib/rbs/wasm/parser.rb

@@ -13,82 +13,90 @@ module RBS
   class Parser
     class << self
       def _parse_signature(buffer, start_pos, end_pos)
-        validate_position_range(start_pos, end_pos)
+        validate_position_range(buffer, start_pos, end_pos)
         encoding = buffer.content.encoding.name
-        success, bytes = WASM::Runtime.instance.parse_signature(buffer.content, encoding, start_pos, end_pos)
-        raise_parsing_error(buffer, bytes) unless success
+        status, bytes = WASM::Runtime.instance.parse_signature(buffer.content, encoding, start_pos, end_pos)
+        raise_parse_failure(buffer, status, bytes, start_pos, end_pos) unless status == WASM::Runtime::OK
 
         WASM::Deserializer.deserialize(bytes, buffer)
       end
 
       def _parse_type(buffer, start_pos, end_pos, variables, require_eof, void_allowed, self_allowed, classish_allowed)
-        validate_position_range(start_pos, end_pos)
+        validate_position_range(buffer, start_pos, end_pos)
         validate_variables(variables)
         encoding = buffer.content.encoding.name
-        success, bytes = WASM::Runtime.instance.parse_type(buffer.content, encoding, start_pos, end_pos, variables, require_eof, void_allowed, self_allowed, classish_allowed)
-        raise_parsing_error(buffer, bytes) unless success
+        status, bytes = WASM::Runtime.instance.parse_type(buffer.content, encoding, start_pos, end_pos, variables, require_eof, void_allowed, self_allowed, classish_allowed)
+        raise_parse_failure(buffer, status, bytes, start_pos, end_pos) unless status == WASM::Runtime::OK
 
         deserialize_or_nil(bytes, buffer)
       end
 
       def _parse_method_type(buffer, start_pos, end_pos, variables, require_eof)
-        validate_position_range(start_pos, end_pos)
+        validate_position_range(buffer, start_pos, end_pos)
         validate_variables(variables)
         encoding = buffer.content.encoding.name
-        success, bytes = WASM::Runtime.instance.parse_method_type(buffer.content, encoding, start_pos, end_pos, variables, require_eof)
-        raise_parsing_error(buffer, bytes) unless success
+        status, bytes = WASM::Runtime.instance.parse_method_type(buffer.content, encoding, start_pos, end_pos, variables, require_eof)
+        raise_parse_failure(buffer, status, bytes, start_pos, end_pos) unless status == WASM::Runtime::OK
 
         deserialize_or_nil(bytes, buffer)
       end
 
       def _parse_type_params(buffer, start_pos, end_pos, module_type_params)
-        validate_position_range(start_pos, end_pos)
+        validate_position_range(buffer, start_pos, end_pos)
         encoding = buffer.content.encoding.name
-        success, bytes = WASM::Runtime.instance.parse_type_params(buffer.content, encoding, start_pos, end_pos, module_type_params)
-        raise_parsing_error(buffer, bytes) unless success
+        status, bytes = WASM::Runtime.instance.parse_type_params(buffer.content, encoding, start_pos, end_pos, module_type_params)
+        raise_parse_failure(buffer, status, bytes, start_pos, end_pos) unless status == WASM::Runtime::OK
 
         bytes.empty? ? nil : WASM::Deserializer.deserialize_node_list(bytes, buffer)
       end
 
       def _lex(buffer, end_pos)
         encoding = buffer.content.encoding.name
-        _success, bytes = WASM::Runtime.instance.lex(buffer.content, encoding, end_pos)
+        _status, bytes = WASM::Runtime.instance.lex(buffer.content, encoding, end_pos)
 
         WASM::Deserializer.deserialize_tokens(bytes, buffer)
       end
 
       def _parse_inline_leading_annotation(buffer, start_pos, end_pos, variables)
-        validate_position_range(start_pos, end_pos)
+        validate_position_range(buffer, start_pos, end_pos)
         validate_variables(variables)
         encoding = buffer.content.encoding.name
-        success, bytes = WASM::Runtime.instance.parse_inline_leading_annotation(buffer.content, encoding, start_pos, end_pos, variables)
-        raise_parsing_error(buffer, bytes) unless success
+        status, bytes = WASM::Runtime.instance.parse_inline_leading_annotation(buffer.content, encoding, start_pos, end_pos, variables)
+        raise_parse_failure(buffer, status, bytes, start_pos, end_pos) unless status == WASM::Runtime::OK
 
         deserialize_or_nil(bytes, buffer)
       end
 
       def _parse_inline_trailing_annotation(buffer, start_pos, end_pos, variables)
-        validate_position_range(start_pos, end_pos)
+        validate_position_range(buffer, start_pos, end_pos)
         validate_variables(variables)
         encoding = buffer.content.encoding.name
-        success, bytes = WASM::Runtime.instance.parse_inline_trailing_annotation(buffer.content, encoding, start_pos, end_pos, variables)
-        raise_parsing_error(buffer, bytes) unless success
+        status, bytes = WASM::Runtime.instance.parse_inline_trailing_annotation(buffer.content, encoding, start_pos, end_pos, variables)
+        raise_parse_failure(buffer, status, bytes, start_pos, end_pos) unless status == WASM::Runtime::OK
 
         deserialize_or_nil(bytes, buffer)
       end
 
       private
 
-      # Reject negative or reversed ranges before handing them to the parser,
-      # matching validate_position_range in the C extension (main.c). A reversed
-      # range would otherwise make the lexer loop forever inside WebAssembly.
-      def validate_position_range(start_pos, end_pos)
+      # Reject the position ranges the parser cannot take, matching
+      # validate_position_range in the C extension (main.c).
+      #
+      # `end_pos` past the end of the buffer is fine: clamping with a large
+      # number instead of measuring the buffer is ordinary, and the lexer stops
+      # at the end of the input on its own.
+      def validate_position_range(buffer, start_pos, end_pos)
         if start_pos < 0 || end_pos < 0
           raise ArgumentError, "negative position range: #{start_pos}...#{end_pos}"
         end
         if start_pos > end_pos
           raise ArgumentError, "invalid position range: #{start_pos}...#{end_pos}"
         end
+
+        size = buffer.content.bytesize
+        if start_pos > size
+          raise ArgumentError, "position range starts past the end of the buffer: #{start_pos}...#{end_pos}, buffer is #{size} bytes"
+        end
       end
 
       # Reject anything that is not nil or an Array of Symbols, matching
@@ -112,6 +120,24 @@ def deserialize_or_nil(bytes, buffer)
         bytes.empty? ? nil : WASM::Deserializer.deserialize(bytes, buffer)
       end
 
+      # Raise for a status other than OK (see rbs_wasm.c).
+      #
+      # A negative status is about the range rather than the source text, so it
+      # comes with an empty result and an ArgumentError, as in the C extension
+      # (main.c). Starting past the end of the buffer is plain from the
+      # buffer's size and rejected above, so a start position that comes back
+      # rejected can only be one inside a character.
+      def raise_parse_failure(buffer, status, bytes, start_pos, end_pos)
+        case status
+        when WASM::Runtime::INVALID_START_POS
+          raise ArgumentError, "position range starts inside a character: #{start_pos}...#{end_pos}"
+        when WASM::Runtime::INVALID_RANGE
+          raise ArgumentError, "invalid position range: #{start_pos}...#{end_pos}"
+        else
+          raise_parsing_error(buffer, bytes)
+        end
+      end
+
       # Decodes the error blob written by set_error_result (rbs_wasm.c) and raises
       # the same error the C extension would (see raise_error in main.c).
       def raise_parsing_error(buffer, blob)

lib/rbs/wasm/runtime.rb

@@ -16,6 +16,14 @@ module WASM
     class Runtime
       include MonitorMixin
 
+      # Statuses the parse entry points return (see rbs_wasm.c). A negative one
+      # is about the range the caller asked for rather than the source text,
+      # and comes with an empty result.
+      INVALID_START_POS = -2
+      INVALID_RANGE = -1
+      PARSE_ERROR = 0
+      OK = 1
+
       class << self
         def instance
           @instance ||= new
@@ -48,9 +56,9 @@ def initialize
       end
 
       # `content` is the whole buffer; `start_pos`/`end_pos` are the character
-      # range within it to parse. Each method returns [success, bytes]: on success
-      # `bytes` is the serialized AST, otherwise it is the error blob (see
-      # set_error_result in rbs_wasm.c).
+      # range within it to parse. Each method returns [status, bytes]: with OK
+      # `bytes` is the serialized AST, with PARSE_ERROR it is the error blob (see
+      # set_error_result in rbs_wasm.c), and with a negative status it is empty.
 
       def parse_signature(content, encoding, start_pos, end_pos)
         run(content, encoding) { |ptr, len, enc_ptr, enc_len| @parse_signature.apply(ptr, len, enc_ptr, enc_len, start_pos, end_pos)[0] }
@@ -118,7 +126,7 @@ def run(source, encoding)
             @memory.write(source_ptr, bytes.to_java_bytes)
             @memory.write(name_ptr, name.to_java_bytes) unless name_length.zero?
             status = yield(source_ptr, length, name_ptr, name_length)
-            [status == 1, read_result]
+            [i32(status), read_result]
           ensure
             @free.apply(source_ptr)
             @free.apply(name_ptr)
@@ -156,6 +164,13 @@ def with_variables(variables)
         end
       end
 
+      # A WebAssembly i32 comes back in a JVM long, so read the low 32 bits as
+      # signed: the negative statuses have to stay negative on this side.
+      def i32(value)
+        value &= 0xFFFF_FFFF
+        value >= 0x8000_0000 ? value - 0x1_0000_0000 : value
+      end
+
       def bool(value)
         value ? 1 : 0
       end

wasm/README.md

@@ -81,10 +81,21 @@ Memory management and results:
 
 Parsing — each takes the whole buffer (`ptr`/`len`), its Ruby encoding name
 (`enc`/`enc_len`, e.g. `"UTF-8"` or `"EUC-JP"`; falls back to UTF-8 when empty or
-unknown), and the character range to parse (`start`/`end`). Each returns `1` on
-success or `0` on a parse error. On success the result is the serialized AST; on
-error it is an error blob (start/end positions, syntax flag, token type,
-message). Type/method-type parsing also takes a buffer of newline-separated
+unknown), and the character range to parse (`start`/`end`). Each returns:
+
+| Status | Meaning | Result |
+| --- | --- | --- |
+| `1` | Parsed. | The serialized AST. |
+| `0` | Parse error. | An error blob (start/end positions, syntax flag, token type, message). |
+| `-1` | Negative or reversed range. | Empty. |
+| `-2` | `start` is a byte position no character starts at — inside a character, or past the end of the buffer. | Empty. |
+
+An `end` past the end of the buffer is not an error: it is clamped to the
+buffer, which is where lexing stops anyway. The two negative statuses are about
+the range the caller asked for rather than the source text, and `RBS::Parser`
+turns both into an `ArgumentError`, as the C extension does.
+
+Type/method-type parsing also takes a buffer of newline-separated
 type-variable names (`vars`/`vars_len`, with `vars_len < 0` meaning "none"):
 
 | Export | Signature |