Rename varint as varuint

Line numbers may be negative, so we need to introduce signed varint,
so renaming unsigned ones first avoid confusion.

Author: byroot

docs/serialization.md

@@ -9,7 +9,7 @@ The syntax tree still requires a copy of the original source, as for the most pa
 
 Let us define some simple types for readability.
 
-### varint
+### varuint
 
 A variable-length integer with the value fitting in `uint32_t` using between 1 and 5 bytes, using the [LEB128](https://en.wikipedia.org/wiki/LEB128) encoding.
 This drastically cuts down on the size of the serialized string, especially when the source file is large.
@@ -18,15 +18,15 @@ This drastically cuts down on the size of the serialized string, especially when
 
 | # bytes | field |
 | --- | --- |
-| varint | the length of the string in bytes |
+| varuint | the length of the string in bytes |
 | ... | the string bytes |
 
 ### location
 
 | # bytes | field |
 | --- | --- |
-| varint | byte offset into the source string where this location begins |
-| varint | length of the location in bytes in the source string |
+| varuint | byte offset into the source string where this location begins |
+| varuint | length of the location in bytes in the source string |
 
 ### comment
 
@@ -71,18 +71,18 @@ The header is structured like the following table:
 | `1` | patch version number |
 | `1` | 1 indicates only semantics fields were serialized, 0 indicates all fields were serialized (including location fields) |
 | string | the encoding name |
-| varint | the start line |
-| varint | number of comments |
+| varuint | the start line |
+| varuint | number of comments |
 | comment* | comments |
-| varint | number of magic comments |
+| varuint | number of magic comments |
 | magic comment* | magic comments |
 | location? | the optional location of the `__END__` keyword and its contents |
-| varint | number of errors |
+| varuint | number of errors |
 | diagnostic* | errors |
-| varint | number of warnings |
+| varuint | number of warnings |
 | diagnostic* | warnings |
 | `4` | content pool offset |
-| varint | content pool size |
+| varuint | content pool size |
 
 After the header comes the body of the serialized string.
 The body consists of a sequence of nodes that is built using a prefix traversal order of the syntax tree.
@@ -159,7 +159,7 @@ serialize(const uint8_t *source, size_t length) {
 }
 ```
 
-The final argument to `pm_serialize_parse` is an optional string that controls the options to the parse function. This includes all of the normal options that could be passed to `pm_parser_init` through a `pm_options_t` struct, but serialized as a string to make it easier for callers through FFI. Note that no `varint` are used here to make it easier to produce the data for the caller, and also serialized size is less important here. The format of the data is structured as follows:
+The final argument to `pm_serialize_parse` is an optional string that controls the options to the parse function. This includes all of the normal options that could be passed to `pm_parser_init` through a `pm_options_t` struct, but serialized as a string to make it easier for callers through FFI. Note that no `varuint` are used here to make it easier to produce the data for the caller, and also serialized size is less important here. The format of the data is structured as follows:
 
 | # bytes | field                      |
 | ------- | -------------------------- |

include/prism/util/pm_buffer.h

@@ -118,7 +118,7 @@ void pm_buffer_append_byte(pm_buffer_t *buffer, uint8_t value);
  * @param buffer The buffer to append to.
  * @param value The integer to append.
  */
-void pm_buffer_append_varint(pm_buffer_t *buffer, uint32_t value);
+void pm_buffer_append_varuint(pm_buffer_t *buffer, uint32_t value);
 
 /**
  * Concatenate one buffer onto another.

src/prism.c

@@ -17268,7 +17268,7 @@ pm_serialize_parse_comments(pm_buffer_t *buffer, const uint8_t *source, size_t s
     pm_node_t *node = pm_parse(&parser);
     pm_serialize_header(buffer);
     pm_serialize_encoding(&parser.encoding, buffer);
-    pm_buffer_append_varint(buffer, parser.start_line);
+    pm_buffer_append_varuint(buffer, parser.start_line);
     pm_serialize_comment_list(&parser, &parser.comment_list, buffer);
 
     pm_node_destroy(&parser, node);

src/util/pm_buffer.c

@@ -138,7 +138,7 @@ pm_buffer_append_byte(pm_buffer_t *buffer, uint8_t value) {
  * Append a 32-bit unsigned integer to the buffer as a variable-length integer.
  */
 void
-pm_buffer_append_varint(pm_buffer_t *buffer, uint32_t value) {
+pm_buffer_append_varuint(pm_buffer_t *buffer, uint32_t value) {
     if (value < 128) {
         pm_buffer_append_byte(buffer, (uint8_t) value);
     } else {

templates/java/org/prism/Loader.java.erb

@@ -104,23 +104,23 @@ public class Loader {
         expect((byte) 1, "Loader.java requires no location fields in the serialized output");
 
         // This loads the name of the encoding.
-        int encodingLength = loadVarInt();
+        int encodingLength = loadVarUInt();
         byte[] encodingNameBytes = new byte[encodingLength];
         buffer.get(encodingNameBytes);
         this.encodingName = new String(encodingNameBytes, StandardCharsets.US_ASCII);
         <%- if string_type == "String" -%>
         this.encodingCharset = getEncodingCharset(this.encodingName);
         <%- end -%>
 
-        source.setStartLine(loadVarInt());
+        source.setStartLine(loadVarUInt());
 
         ParseResult.MagicComment[] magicComments = loadMagicComments();
         Nodes.Location dataLocation = loadOptionalLocation();
         ParseResult.Error[] errors = loadSyntaxErrors();
         ParseResult.Warning[] warnings = loadWarnings();
 
         int constantPoolBufferOffset = buffer.getInt();
-        int constantPoolLength = loadVarInt();
+        int constantPoolLength = loadVarUInt();
         this.constantPool = new ConstantPool(this, source.bytes, constantPoolBufferOffset, constantPoolLength);
 
         Nodes.Node node = loadNode();
@@ -138,7 +138,7 @@ public class Loader {
     }
 
     private byte[] loadEmbeddedString() {
-        int length = loadVarInt();
+        int length = loadVarUInt();
         byte[] bytes = new byte[length];
         buffer.get(bytes);
         return bytes;
@@ -147,8 +147,8 @@ public class Loader {
     private byte[] loadString() {
         switch (buffer.get()) {
             case 1:
-                int start = loadVarInt();
-                int length = loadVarInt();
+                int start = loadVarUInt();
+                int length = loadVarUInt();
                 byte[] bytes = new byte[length];
                 System.arraycopy(source.bytes, start, bytes, 0, length);
                 return bytes;
@@ -160,7 +160,7 @@ public class Loader {
     }
 
     private ParseResult.MagicComment[] loadMagicComments() {
-        int count = loadVarInt();
+        int count = loadVarUInt();
         ParseResult.MagicComment[] magicComments = new ParseResult.MagicComment[count];
 
         for (int i = 0; i < count; i++) {
@@ -175,7 +175,7 @@ public class Loader {
     }
 
     private ParseResult.Error[] loadSyntaxErrors() {
-        int count = loadVarInt();
+        int count = loadVarUInt();
         ParseResult.Error[] errors = new ParseResult.Error[count];
 
         // error messages only contain ASCII characters
@@ -192,7 +192,7 @@ public class Loader {
     }
 
     private ParseResult.Warning[] loadWarnings() {
-        int count = loadVarInt();
+        int count = loadVarUInt();
         ParseResult.Warning[] warnings = new ParseResult.Warning[count];
 
         // warning messages only contain ASCII characters
@@ -218,7 +218,7 @@ public class Loader {
     }
 
     private <%= string_type %> loadConstant() {
-        return constantPool.get(buffer, loadVarInt());
+        return constantPool.get(buffer, loadVarUInt());
     }
 
     private <%= string_type %> loadOptionalConstant() {
@@ -231,19 +231,19 @@ public class Loader {
     }
 
     private <%= string_type %>[] loadConstants() {
-        int length = loadVarInt();
+        int length = loadVarUInt();
         if (length == 0) {
             return Nodes.EMPTY_STRING_ARRAY;
         }
         <%= string_type %>[] constants = new <%= string_type %>[length];
         for (int i = 0; i < length; i++) {
-            constants[i] = constantPool.get(buffer, loadVarInt());
+            constants[i] = constantPool.get(buffer, loadVarUInt());
         }
         return constants;
     }
 
     private Nodes.Node[] loadNodes() {
-        int length = loadVarInt();
+        int length = loadVarUInt();
         if (length == 0) {
             return Nodes.Node.EMPTY_ARRAY;
         }
@@ -255,7 +255,7 @@ public class Loader {
     }
 
     private Nodes.Location loadLocation() {
-        return new Nodes.Location(loadVarInt(), loadVarInt());
+        return new Nodes.Location(loadVarUInt(), loadVarUInt());
     }
 
     private Nodes.Location loadOptionalLocation() {
@@ -267,7 +267,7 @@ public class Loader {
     }
 
     // From https://github.com/protocolbuffers/protobuf/blob/v23.1/java/core/src/main/java/com/google/protobuf/BinaryReader.java#L1507
-    private int loadVarInt() {
+    private int loadVarUInt() {
         int x;
         if ((x = buffer.get()) >= 0) {
             return x;
@@ -285,15 +285,15 @@ public class Loader {
     }
 
     private short loadFlags() {
-        int flags = loadVarInt();
+        int flags = loadVarUInt();
         assert flags >= 0 && flags <= Short.MAX_VALUE;
         return (short) flags;
     }
 
     private Nodes.Node loadNode() {
         int type = buffer.get() & 0xFF;
-        int startOffset = loadVarInt();
-        int length = loadVarInt();
+        int startOffset = loadVarUInt();
+        int length = loadVarUInt();
 
         switch (type) {
             <%- nodes.each_with_index do |node, index| -%>
@@ -311,7 +311,7 @@ public class Loader {
               when Prism::ConstantListField then "loadConstants()"
               when Prism::LocationField then "loadLocation()"
               when Prism::OptionalLocationField then "loadOptionalLocation()"
-              when Prism::UInt32Field then "loadVarInt()"
+              when Prism::UInt32Field then "loadVarUInt()"
               when Prism::FlagsField then "loadFlags()"
               else raise
               end

templates/lib/prism/serialize.rb.erb

@@ -73,18 +73,18 @@ module Prism
       end
 
       def load_encoding
-        @encoding = Encoding.find(io.read(load_varint))
+        @encoding = Encoding.find(io.read(load_varuint))
         @input = input.force_encoding(@encoding).freeze
         @encoding
       end
 
       def load_start_line
-        source.start_line = load_varint
+        source.start_line = load_varuint
       end
 
       def load_comments
-        load_varint.times.map do
-          case load_varint
+        load_varuint.times.map do
+          case load_varuint
           when 0 then InlineComment.new(load_location)
           when 1 then EmbDocComment.new(load_location)
           when 2 then DATAComment.new(load_location)
@@ -94,19 +94,19 @@ module Prism
 
       def load_metadata
         comments = load_comments
-        magic_comments = load_varint.times.map { MagicComment.new(load_location, load_location) }
+        magic_comments = load_varuint.times.map { MagicComment.new(load_location, load_location) }
         data_loc = load_optional_location
-        errors = load_varint.times.map { ParseError.new(load_embedded_string, load_location) }
-        warnings = load_varint.times.map { ParseWarning.new(load_embedded_string, load_location) }
+        errors = load_varuint.times.map { ParseError.new(load_embedded_string, load_location) }
+        warnings = load_varuint.times.map { ParseWarning.new(load_embedded_string, load_location) }
         [comments, magic_comments, data_loc, errors, warnings]
       end
 
       def load_tokens
         tokens = []
-        while type = TOKEN_TYPES.fetch(load_varint)
-          start = load_varint
-          length = load_varint
-          lex_state = load_varint
+        while type = TOKEN_TYPES.fetch(load_varuint)
+          start = load_varuint
+          length = load_varuint
+          lex_state = load_varuint
           location = Location.new(@source, start, length)
           tokens << [Prism::Token.new(type, location.slice, location), lex_state]
         end
@@ -133,7 +133,7 @@ module Prism
         comments, magic_comments, data_loc, errors, warnings = load_metadata
 
         @constant_pool_offset = io.read(4).unpack1("L")
-        @constant_pool = Array.new(load_varint, nil)
+        @constant_pool = Array.new(load_varuint, nil)
 
         [load_node, comments, magic_comments, data_loc, errors, warnings]
       end
@@ -147,7 +147,7 @@ module Prism
 
       # variable-length integer using https://en.wikipedia.org/wiki/LEB128
       # This is also what protobuf uses: https://protobuf.dev/programming-guides/encoding/#varints
-      def load_varint
+      def load_varuint
         n = io.getbyte
         if n < 128
           n
@@ -173,14 +173,14 @@ module Prism
       end
 
       def load_embedded_string
-        io.read(load_varint).force_encoding(encoding)
+        io.read(load_varuint).force_encoding(encoding)
       end
 
       def load_string
         type = io.getbyte
         case type
         when 1
-          input.byteslice(load_varint, load_varint).force_encoding(encoding)
+          input.byteslice(load_varuint, load_varuint).force_encoding(encoding)
         when 2
           load_embedded_string
         else
@@ -189,7 +189,7 @@ module Prism
       end
 
       def load_location
-        Location.new(source, load_varint, load_varint)
+        Location.new(source, load_varuint, load_varuint)
       end
 
       def load_optional_location
@@ -218,11 +218,11 @@ module Prism
       end
 
       def load_required_constant
-        load_constant(load_varint - 1)
+        load_constant(load_varuint - 1)
       end
 
       def load_optional_constant
-        index = load_varint
+        index = load_varuint
         load_constant(index - 1) if index != 0
       end
 
@@ -242,13 +242,13 @@ module Prism
               when Prism::NodeField then "load_node"
               when Prism::OptionalNodeField then "load_optional_node"
               when Prism::StringField then "load_string"
-              when Prism::NodeListField then "Array.new(load_varint) { load_node }"
+              when Prism::NodeListField then "Array.new(load_varuint) { load_node }"
               when Prism::ConstantField then "load_required_constant"
               when Prism::OptionalConstantField then "load_optional_constant"
-              when Prism::ConstantListField then "Array.new(load_varint) { load_required_constant }"
+              when Prism::ConstantListField then "Array.new(load_varuint) { load_required_constant }"
               when Prism::LocationField then "load_location"
               when Prism::OptionalLocationField then "load_optional_location"
-              when Prism::UInt32Field, Prism::FlagsField then "load_varint"
+              when Prism::UInt32Field, Prism::FlagsField then "load_varuint"
               else raise
               end
             } + ["location"]).join(", ") -%>)
@@ -275,13 +275,13 @@ module Prism
                 when Prism::NodeField then "load_node"
                 when Prism::OptionalNodeField then "load_optional_node"
                 when Prism::StringField then "load_string"
-                when Prism::NodeListField then "Array.new(load_varint) { load_node }"
+                when Prism::NodeListField then "Array.new(load_varuint) { load_node }"
                 when Prism::ConstantField then "load_required_constant"
                 when Prism::OptionalConstantField then "load_optional_constant"
-                when Prism::ConstantListField then "Array.new(load_varint) { load_required_constant }"
+                when Prism::ConstantListField then "Array.new(load_varuint) { load_required_constant }"
                 when Prism::LocationField then "load_location"
                 when Prism::OptionalLocationField then "load_optional_location"
-                when Prism::UInt32Field, Prism::FlagsField then "load_varint"
+                when Prism::UInt32Field, Prism::FlagsField then "load_varuint"
                 else raise
                 end
               } + ["location"]).join(", ") -%>)