debase-ruby_core_source 3.3.0 → 3.3.1

data/lib/debase/ruby_core_source/ruby-3.3.0-p0/prism/prettyprint.h

@@ -0,0 +1,26 @@
+/**
+ * @file prettyprint.h
+ *
+ * An AST node pretty-printer.
+ */
+#ifndef PRISM_PRETTYPRINT_H
+#define PRISM_PRETTYPRINT_H
+
+#include "prism/defines.h"
+
+#include <stdio.h>
+
+#include "prism/ast.h"
+#include "prism/parser.h"
+#include "prism/util/pm_buffer.h"
+
+/**
+ * Pretty-prints the AST represented by the given node to the given buffer.
+ *
+ * @param output_buffer The buffer to write the pretty-printed AST to.
+ * @param parser The parser that parsed the AST.
+ * @param node The root node of the AST to pretty-print.
+ */
+PRISM_EXPORTED_FUNCTION void pm_prettyprint(pm_buffer_t *output_buffer, const pm_parser_t *parser, const pm_node_t *node);
+
+#endif

data/lib/debase/ruby_core_source/ruby-3.3.0-p0/prism/prism.h

@@ -0,0 +1,272 @@
+/**
+ * @file prism.h
+ *
+ * The main header file for the prism parser.
+ */
+#ifndef PRISM_H
+#define PRISM_H
+
+#include "prism/defines.h"
+#include "prism/util/pm_buffer.h"
+#include "prism/util/pm_char.h"
+#include "prism/util/pm_memchr.h"
+#include "prism/util/pm_strncasecmp.h"
+#include "prism/util/pm_strpbrk.h"
+#include "prism/ast.h"
+#include "prism/diagnostic.h"
+#include "prism/node.h"
+#include "prism/options.h"
+#include "prism/pack.h"
+#include "prism/parser.h"
+#include "prism/prettyprint.h"
+#include "prism/regexp.h"
+#include "prism/version.h"
+
+#include <assert.h>
+#include <errno.h>
+#include <stdarg.h>
+#include <stdbool.h>
+#include <stdint.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+
+#ifndef _WIN32
+#include <strings.h>
+#endif
+
+/**
+ * The prism version and the serialization format.
+ *
+ * @returns The prism version as a constant string.
+ */
+PRISM_EXPORTED_FUNCTION const char * pm_version(void);
+
+/**
+ * Initialize a parser with the given start and end pointers.
+ *
+ * @param parser The parser to initialize.
+ * @param source The source to parse.
+ * @param size The size of the source.
+ * @param options The optional options to use when parsing.
+ */
+PRISM_EXPORTED_FUNCTION void pm_parser_init(pm_parser_t *parser, const uint8_t *source, size_t size, const pm_options_t *options);
+
+/**
+ * Register a callback that will be called whenever prism changes the encoding
+ * it is using to parse based on the magic comment.
+ *
+ * @param parser The parser to register the callback with.
+ * @param callback The callback to register.
+ */
+PRISM_EXPORTED_FUNCTION void pm_parser_register_encoding_changed_callback(pm_parser_t *parser, pm_encoding_changed_callback_t callback);
+
+/**
+ * Free any memory associated with the given parser.
+ *
+ * @param parser The parser to free.
+ */
+PRISM_EXPORTED_FUNCTION void pm_parser_free(pm_parser_t *parser);
+
+/**
+ * Initiate the parser with the given parser.
+ *
+ * @param parser The parser to use.
+ * @return The AST representing the source.
+ */
+PRISM_EXPORTED_FUNCTION pm_node_t * pm_parse(pm_parser_t *parser);
+
+/**
+ * Serialize the given list of comments to the given buffer.
+ *
+ * @param parser The parser to serialize.
+ * @param list The list of comments to serialize.
+ * @param buffer The buffer to serialize to.
+ */
+void pm_serialize_comment_list(pm_parser_t *parser, pm_list_t *list, pm_buffer_t *buffer);
+
+/**
+ * Serialize the name of the encoding to the buffer.
+ *
+ * @param encoding The encoding to serialize.
+ * @param buffer The buffer to serialize to.
+ */
+void pm_serialize_encoding(const pm_encoding_t *encoding, pm_buffer_t *buffer);
+
+/**
+ * Serialize the encoding, metadata, nodes, and constant pool.
+ *
+ * @param parser The parser to serialize.
+ * @param node The node to serialize.
+ * @param buffer The buffer to serialize to.
+ */
+void pm_serialize_content(pm_parser_t *parser, pm_node_t *node, pm_buffer_t *buffer);
+
+/**
+ * Serialize the AST represented by the given node to the given buffer.
+ *
+ * @param parser The parser to serialize.
+ * @param node The node to serialize.
+ * @param buffer The buffer to serialize to.
+ */
+PRISM_EXPORTED_FUNCTION void pm_serialize(pm_parser_t *parser, pm_node_t *node, pm_buffer_t *buffer);
+
+/**
+ * Parse the given source to the AST and dump the AST to the given buffer.
+ *
+ * @param buffer The buffer to serialize to.
+ * @param source The source to parse.
+ * @param size The size of the source.
+ * @param data The optional data to pass to the parser.
+ */
+PRISM_EXPORTED_FUNCTION void pm_serialize_parse(pm_buffer_t *buffer, const uint8_t *source, size_t size, const char *data);
+
+/**
+ * Parse and serialize the comments in the given source to the given buffer.
+ *
+ * @param buffer The buffer to serialize to.
+ * @param source The source to parse.
+ * @param size The size of the source.
+ * @param data The optional data to pass to the parser.
+ */
+PRISM_EXPORTED_FUNCTION void pm_serialize_parse_comments(pm_buffer_t *buffer, const uint8_t *source, size_t size, const char *data);
+
+/**
+ * Lex the given source and serialize to the given buffer.
+ *
+ * @param source The source to lex.
+ * @param size The size of the source.
+ * @param buffer The buffer to serialize to.
+ * @param data The optional data to pass to the lexer.
+ */
+PRISM_EXPORTED_FUNCTION void pm_serialize_lex(pm_buffer_t *buffer, const uint8_t *source, size_t size, const char *data);
+
+/**
+ * Parse and serialize both the AST and the tokens represented by the given
+ * source to the given buffer.
+ *
+ * @param buffer The buffer to serialize to.
+ * @param source The source to parse.
+ * @param size The size of the source.
+ * @param data The optional data to pass to the parser.
+ */
+PRISM_EXPORTED_FUNCTION void pm_serialize_parse_lex(pm_buffer_t *buffer, const uint8_t *source, size_t size, const char *data);
+
+/**
+ * Parse the source and return true if it parses without errors or warnings.
+ *
+ * @param source The source to parse.
+ * @param size The size of the source.
+ * @param data The optional data to pass to the parser.
+ * @return True if the source parses without errors or warnings.
+ */
+PRISM_EXPORTED_FUNCTION bool pm_parse_success_p(const uint8_t *source, size_t size, const char *data);
+
+/**
+ * Returns a string representation of the given token type.
+ *
+ * @param token_type The token type to convert to a string.
+ * @return A string representation of the given token type.
+ */
+PRISM_EXPORTED_FUNCTION const char * pm_token_type_to_str(pm_token_type_t token_type);
+
+/**
+ * @mainpage
+ *
+ * Prism is a parser for the Ruby programming language. It is designed to be
+ * portable, error tolerant, and maintainable. It is written in C99 and has no
+ * dependencies. It is currently being integrated into
+ * [CRuby](https://github.com/ruby/ruby),
+ * [JRuby](https://github.com/jruby/jruby),
+ * [TruffleRuby](https://github.com/oracle/truffleruby),
+ * [Sorbet](https://github.com/sorbet/sorbet), and
+ * [Syntax Tree](https://github.com/ruby-syntax-tree/syntax_tree).
+ *
+ * @section getting-started Getting started
+ *
+ * If you're vendoring this project and compiling it statically then as long as
+ * you have a C99 compiler you will be fine. If you're linking against it as
+ * shared library, then you should compile with `-fvisibility=hidden` and
+ * `-DPRISM_EXPORT_SYMBOLS` to tell prism to make only its public interface
+ * visible.
+ *
+ * @section parsing Parsing
+ *
+ * In order to parse Ruby code, the structures and functions that you're going
+ * to want to use and be aware of are:
+ *
+ * * `pm_parser_t` - the main parser structure
+ * * `pm_parser_init` - initialize a parser
+ * * `pm_parse` - parse and return the root node
+ * * `pm_node_destroy` - deallocate the root node returned by `pm_parse`
+ * * `pm_parser_free` - free the internal memory of the parser
+ *
+ * Putting all of this together would look something like:
+ *
+ * ```c
+ * void parse(const uint8_t *source, size_t length) {
+ *     pm_parser_t parser;
+ *     pm_parser_init(&parser, source, length, NULL);
+ *
+ *     pm_node_t *root = pm_parse(&parser);
+ *     printf("PARSED!\n");
+ *
+ *     pm_node_destroy(&parser, root);
+ *     pm_parser_free(&parser);
+ * }
+ * ```
+ *
+ * All of the nodes "inherit" from `pm_node_t` by embedding those structures as
+ * their first member. This means you can downcast and upcast any node in the
+ * tree to a `pm_node_t`.
+ *
+ * @section serializing Serializing
+ *
+ * Prism provides the ability to serialize the AST and its related metadata into
+ * a binary format. This format is designed to be portable to different
+ * languages and runtimes so that you only need to make one FFI call in order to
+ * parse Ruby code. The structures and functions that you're going to want to
+ * use and be aware of are:
+ *
+ * * `pm_buffer_t` - a small buffer object that will hold the serialized AST
+ * * `pm_buffer_free` - free the memory associated with the buffer
+ * * `pm_serialize` - serialize the AST into a buffer
+ * * `pm_serialize_parse` - parse and serialize the AST into a buffer
+ *
+ * Putting all of this together would look something like:
+ *
+ * ```c
+ * void serialize(const uint8_t *source, size_t length) {
+ *     pm_buffer_t buffer = { 0 };
+ *
+ *     pm_serialize_parse(&buffer, source, length, NULL);
+ *     printf("SERIALIZED!\n");
+ *
+ *     pm_buffer_free(&buffer);
+ * }
+ * ```
+ *
+ * @section inspecting Inspecting
+ *
+ * Prism provides the ability to inspect the AST by pretty-printing nodes. You
+ * can do this with the `pm_prettyprint` function, which you would use like:
+ *
+ * ```c
+ * void prettyprint(const uint8_t *source, size_t length) {
+ *     pm_parser_t parser;
+ *     pm_parser_init(&parser, source, length, NULL);
+ *
+ *     pm_node_t *root = pm_parse(&parser);
+ *     pm_buffer_t buffer = { 0 };
+ *
+ *     pm_prettyprint(&buffer, &parser, root);
+ *     printf("*.s%\n", (int) buffer.length, buffer.value);
+ *
+ *     pm_buffer_free(&buffer);
+ *     pm_node_destroy(&parser, root);
+ *     pm_parser_free(&parser);
+ * }
+ * ```
+ */
+
+#endif

data/lib/debase/ruby_core_source/ruby-3.3.0-p0/prism/regexp.h

@@ -0,0 +1,33 @@
+/**
+ * @file regexp.h
+ *
+ * A regular expression parser.
+ */
+#ifndef PRISM_REGEXP_H
+#define PRISM_REGEXP_H
+
+#include "prism/defines.h"
+#include "prism/parser.h"
+#include "prism/encoding.h"
+#include "prism/util/pm_memchr.h"
+#include "prism/util/pm_string_list.h"
+#include "prism/util/pm_string.h"
+
+#include <stdbool.h>
+#include <stddef.h>
+#include <string.h>
+
+/**
+ * Parse a regular expression and extract the names of all of the named capture
+ * groups.
+ *
+ * @param source The source code to parse.
+ * @param size The size of the source code.
+ * @param named_captures The list to add the names of the named capture groups.
+ * @param encoding_changed Whether or not the encoding changed from the default.
+ * @param encoding The encoding of the source code.
+ * @return Whether or not the parsing was successful.
+ */
+PRISM_EXPORTED_FUNCTION bool pm_regexp_named_capture_group_names(const uint8_t *source, size_t size, pm_string_list_t *named_captures, bool encoding_changed, const pm_encoding_t *encoding);
+
+#endif

data/lib/debase/ruby_core_source/ruby-3.3.0-p0/prism/util/pm_buffer.h

@@ -0,0 +1,146 @@
+/**
+ * @file pm_buffer.h
+ *
+ * A wrapper around a contiguous block of allocated memory.
+ */
+#ifndef PRISM_BUFFER_H
+#define PRISM_BUFFER_H
+
+#include "prism/defines.h"
+
+#include <assert.h>
+#include <stdbool.h>
+#include <stdint.h>
+#include <stdlib.h>
+#include <string.h>
+
+/**
+ * A pm_buffer_t is a simple memory buffer that stores data in a contiguous
+ * block of memory.
+ */
+typedef struct {
+    /** The length of the buffer in bytes. */
+    size_t length;
+
+    /** The capacity of the buffer in bytes that has been allocated. */
+    size_t capacity;
+
+    /** A pointer to the start of the buffer. */
+    char *value;
+} pm_buffer_t;
+
+/**
+ * Return the size of the pm_buffer_t struct.
+ *
+ * @returns The size of the pm_buffer_t struct.
+ */
+PRISM_EXPORTED_FUNCTION size_t pm_buffer_sizeof(void);
+
+/**
+ * Initialize a pm_buffer_t with the given capacity.
+ *
+ * @param buffer The buffer to initialize.
+ * @param capacity The capacity of the buffer.
+ * @returns True if the buffer was initialized successfully, false otherwise.
+ */
+bool pm_buffer_init_capacity(pm_buffer_t *buffer, size_t capacity);
+
+/**
+ * Initialize a pm_buffer_t with its default values.
+ *
+ * @param buffer The buffer to initialize.
+ * @returns True if the buffer was initialized successfully, false otherwise.
+ */
+PRISM_EXPORTED_FUNCTION bool pm_buffer_init(pm_buffer_t *buffer);
+
+/**
+ * Return the value of the buffer.
+ *
+ * @param buffer The buffer to get the value of.
+ * @returns The value of the buffer.
+ */
+PRISM_EXPORTED_FUNCTION char * pm_buffer_value(pm_buffer_t *buffer);
+
+/**
+ * Return the length of the buffer.
+ *
+ * @param buffer The buffer to get the length of.
+ * @returns The length of the buffer.
+ */
+PRISM_EXPORTED_FUNCTION size_t pm_buffer_length(pm_buffer_t *buffer);
+
+/**
+ * Append the given amount of space as zeroes to the buffer.
+ *
+ * @param buffer The buffer to append to.
+ * @param length The amount of space to append and zero.
+ */
+void pm_buffer_append_zeroes(pm_buffer_t *buffer, size_t length);
+
+/**
+ * Append a formatted string to the buffer.
+ *
+ * @param buffer The buffer to append to.
+ * @param format The format string to append.
+ * @param ... The arguments to the format string.
+ */
+void pm_buffer_append_format(pm_buffer_t *buffer, const char *format, ...) PRISM_ATTRIBUTE_FORMAT(2, 3);
+
+/**
+ * Append a string to the buffer.
+ *
+ * @param buffer The buffer to append to.
+ * @param value The string to append.
+ * @param length The length of the string to append.
+ */
+void pm_buffer_append_string(pm_buffer_t *buffer, const char *value, size_t length);
+
+/**
+ * Append a list of bytes to the buffer.
+ *
+ * @param buffer The buffer to append to.
+ * @param value The bytes to append.
+ * @param length The length of the bytes to append.
+ */
+void pm_buffer_append_bytes(pm_buffer_t *buffer, const uint8_t *value, size_t length);
+
+/**
+ * Append a single byte to the buffer.
+ *
+ * @param buffer The buffer to append to.
+ * @param value The byte to append.
+ */
+void 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.
+ *
+ * @param buffer The buffer to append to.
+ * @param value The integer to append.
+ */
+void pm_buffer_append_varuint(pm_buffer_t *buffer, uint32_t value);
+
+/**
+ * Append a 32-bit signed integer to the buffer as a variable-length integer.
+ *
+ * @param buffer The buffer to append to.
+ * @param value The integer to append.
+ */
+void pm_buffer_append_varsint(pm_buffer_t *buffer, int32_t value);
+
+/**
+ * Concatenate one buffer onto another.
+ *
+ * @param destination The buffer to concatenate onto.
+ * @param source The buffer to concatenate.
+ */
+void pm_buffer_concat(pm_buffer_t *destination, const pm_buffer_t *source);
+
+/**
+ * Free the memory associated with the buffer.
+ *
+ * @param buffer The buffer to free.
+ */
+PRISM_EXPORTED_FUNCTION void pm_buffer_free(pm_buffer_t *buffer);
+
+#endif

data/lib/debase/ruby_core_source/ruby-3.3.0-p0/prism/util/pm_char.h

@@ -0,0 +1,205 @@
+/**
+ * @file pm_char.h
+ *
+ * Functions for working with characters and strings.
+ */
+#ifndef PRISM_CHAR_H
+#define PRISM_CHAR_H
+
+#include "prism/defines.h"
+#include "prism/util/pm_newline_list.h"
+
+#include <stdbool.h>
+#include <stddef.h>
+
+/**
+ * Returns the number of characters at the start of the string that are
+ * whitespace. Disallows searching past the given maximum number of characters.
+ *
+ * @param string The string to search.
+ * @param length The maximum number of characters to search.
+ * @return The number of characters at the start of the string that are
+ *     whitespace.
+ */
+size_t pm_strspn_whitespace(const uint8_t *string, ptrdiff_t length);
+
+/**
+ * Returns the number of characters at the start of the string that are
+ * whitespace while also tracking the location of each newline. Disallows
+ * searching past the given maximum number of characters.
+ *
+ * @param string The string to search.
+ * @param length The maximum number of characters to search.
+ * @param newline_list The list of newlines to populate.
+ * @return The number of characters at the start of the string that are
+ *     whitespace.
+ */
+size_t
+pm_strspn_whitespace_newlines(const uint8_t *string, ptrdiff_t length, pm_newline_list_t *newline_list);
+
+/**
+ * Returns the number of characters at the start of the string that are inline
+ * whitespace. Disallows searching past the given maximum number of characters.
+ *
+ * @param string The string to search.
+ * @param length The maximum number of characters to search.
+ * @return The number of characters at the start of the string that are inline
+ *     whitespace.
+ */
+size_t pm_strspn_inline_whitespace(const uint8_t *string, ptrdiff_t length);
+
+/**
+ * Returns the number of characters at the start of the string that are decimal
+ * digits. Disallows searching past the given maximum number of characters.
+ *
+ * @param string The string to search.
+ * @param length The maximum number of characters to search.
+ * @return The number of characters at the start of the string that are decimal
+ *     digits.
+ */
+size_t pm_strspn_decimal_digit(const uint8_t *string, ptrdiff_t length);
+
+/**
+ * Returns the number of characters at the start of the string that are
+ * hexadecimal digits. Disallows searching past the given maximum number of
+ * characters.
+ *
+ * @param string The string to search.
+ * @param length The maximum number of characters to search.
+ * @return The number of characters at the start of the string that are
+ *     hexadecimal digits.
+ */
+size_t pm_strspn_hexadecimal_digit(const uint8_t *string, ptrdiff_t length);
+
+/**
+ * Returns the number of characters at the start of the string that are octal
+ * digits or underscores. Disallows searching past the given maximum number of
+ * characters.
+ *
+ * If multiple underscores are found in a row or if an underscore is
+ * found at the end of the number, then the invalid pointer is set to the index
+ * of the first invalid underscore.
+ *
+ * @param string The string to search.
+ * @param length The maximum number of characters to search.
+ * @param invalid The pointer to set to the index of the first invalid
+ *     underscore.
+ * @return The number of characters at the start of the string that are octal
+ *     digits or underscores.
+ */
+size_t pm_strspn_octal_number(const uint8_t *string, ptrdiff_t length, const uint8_t **invalid);
+
+/**
+ * Returns the number of characters at the start of the string that are decimal
+ * digits or underscores. Disallows searching past the given maximum number of
+ * characters.
+ *
+ * If multiple underscores are found in a row or if an underscore is
+ * found at the end of the number, then the invalid pointer is set to the index
+ * of the first invalid underscore.
+ *
+ * @param string The string to search.
+ * @param length The maximum number of characters to search.
+ * @param invalid The pointer to set to the index of the first invalid
+ *     underscore.
+ * @return The number of characters at the start of the string that are decimal
+ *     digits or underscores.
+ */
+size_t pm_strspn_decimal_number(const uint8_t *string, ptrdiff_t length, const uint8_t **invalid);
+
+/**
+ * Returns the number of characters at the start of the string that are
+ * hexadecimal digits or underscores. Disallows searching past the given maximum
+ * number of characters.
+ *
+ * If multiple underscores are found in a row or if an underscore is
+ * found at the end of the number, then the invalid pointer is set to the index
+ * of the first invalid underscore.
+ *
+ * @param string The string to search.
+ * @param length The maximum number of characters to search.
+ * @param invalid The pointer to set to the index of the first invalid
+ *     underscore.
+ * @return The number of characters at the start of the string that are
+ *     hexadecimal digits or underscores.
+ */
+size_t pm_strspn_hexadecimal_number(const uint8_t *string, ptrdiff_t length, const uint8_t **invalid);
+
+/**
+ * Returns the number of characters at the start of the string that are regexp
+ * options. Disallows searching past the given maximum number of characters.
+ *
+ * @param string The string to search.
+ * @param length The maximum number of characters to search.
+ * @return The number of characters at the start of the string that are regexp
+ *     options.
+ */
+size_t pm_strspn_regexp_option(const uint8_t *string, ptrdiff_t length);
+
+/**
+ * Returns the number of characters at the start of the string that are binary
+ * digits or underscores. Disallows searching past the given maximum number of
+ * characters.
+ *
+ * If multiple underscores are found in a row or if an underscore is
+ * found at the end of the number, then the invalid pointer is set to the index
+ * of the first invalid underscore.
+ *
+ * @param string The string to search.
+ * @param length The maximum number of characters to search.
+ * @param invalid The pointer to set to the index of the first invalid
+ *     underscore.
+ * @return The number of characters at the start of the string that are binary
+ *     digits or underscores.
+ */
+size_t pm_strspn_binary_number(const uint8_t *string, ptrdiff_t length, const uint8_t **invalid);
+
+/**
+ * Returns true if the given character is a whitespace character.
+ *
+ * @param b The character to check.
+ * @return True if the given character is a whitespace character.
+ */
+bool pm_char_is_whitespace(const uint8_t b);
+
+/**
+ * Returns true if the given character is an inline whitespace character.
+ *
+ * @param b The character to check.
+ * @return True if the given character is an inline whitespace character.
+ */
+bool pm_char_is_inline_whitespace(const uint8_t b);
+
+/**
+ * Returns true if the given character is a binary digit.
+ *
+ * @param b The character to check.
+ * @return True if the given character is a binary digit.
+ */
+bool pm_char_is_binary_digit(const uint8_t b);
+
+/**
+ * Returns true if the given character is an octal digit.
+ *
+ * @param b The character to check.
+ * @return True if the given character is an octal digit.
+ */
+bool pm_char_is_octal_digit(const uint8_t b);
+
+/**
+ * Returns true if the given character is a decimal digit.
+ *
+ * @param b The character to check.
+ * @return True if the given character is a decimal digit.
+ */
+bool pm_char_is_decimal_digit(const uint8_t b);
+
+/**
+ * Returns true if the given character is a hexadecimal digit.
+ *
+ * @param b The character to check.
+ * @return True if the given character is a hexadecimal digit.
+ */
+bool pm_char_is_hexadecimal_digit(const uint8_t b);
+
+#endif