prism 2.0.0-arm-linux-musl

data/include/prism/internal/diagnostic.h

@@ -0,0 +1,389 @@
+/*----------------------------------------------------------------------------*/
+/* This file is generated by the templates/template.rb script and should not  */
+/* be modified manually. See                                                  */
+/* templates/include/prism/internal/diagnostic.h.erb                          */
+/* if you are looking to modify the                                           */
+/* template                                                                   */
+/*----------------------------------------------------------------------------*/
+
+#ifndef PRISM_INTERNAL_DIAGNOSTIC_H
+#define PRISM_INTERNAL_DIAGNOSTIC_H
+
+#include "prism/internal/list.h"
+
+#include "prism/arena.h"
+#include "prism/diagnostic.h"
+
+/*
+ * The diagnostic IDs of all of the diagnostics, used to communicate the types
+ * of errors between the parser and the user.
+ */
+typedef enum {
+    /* These are the error diagnostics. */
+    PM_ERR_ALIAS_ARGUMENT,
+    PM_ERR_ALIAS_ARGUMENT_NUMBERED_REFERENCE,
+    PM_ERR_AMPAMPEQ_MULTI_ASSIGN,
+    PM_ERR_ARGUMENT_AFTER_BLOCK,
+    PM_ERR_ARGUMENT_AFTER_FORWARDING_ELLIPSES,
+    PM_ERR_ARGUMENT_BARE_HASH,
+    PM_ERR_ARGUMENT_BLOCK_MULTI,
+    PM_ERR_ARGUMENT_CONFLICT_AMPERSAND,
+    PM_ERR_ARGUMENT_CONFLICT_STAR,
+    PM_ERR_ARGUMENT_CONFLICT_STAR_STAR,
+    PM_ERR_ARGUMENT_FORMAL_CLASS,
+    PM_ERR_ARGUMENT_FORMAL_CONSTANT,
+    PM_ERR_ARGUMENT_FORMAL_GLOBAL,
+    PM_ERR_ARGUMENT_FORMAL_IVAR,
+    PM_ERR_ARGUMENT_FORWARDING_UNBOUND,
+    PM_ERR_ARGUMENT_NO_FORWARDING_AMPERSAND,
+    PM_ERR_ARGUMENT_NO_FORWARDING_ELLIPSES,
+    PM_ERR_ARGUMENT_NO_FORWARDING_ELLIPSES_LAMBDA,
+    PM_ERR_ARGUMENT_NO_FORWARDING_ELLIPSES_BLOCK,
+    PM_ERR_ARGUMENT_NO_FORWARDING_STAR,
+    PM_ERR_ARGUMENT_NO_FORWARDING_STAR_STAR,
+    PM_ERR_ARGUMENT_SPLAT_AFTER_ASSOC_SPLAT,
+    PM_ERR_ARGUMENT_SPLAT_AFTER_SPLAT,
+    PM_ERR_ARGUMENT_TERM_PAREN,
+    PM_ERR_ARGUMENT_UNEXPECTED_BLOCK,
+    PM_ERR_ARRAY_ELEMENT,
+    PM_ERR_ARRAY_EXPRESSION,
+    PM_ERR_ARRAY_EXPRESSION_AFTER_STAR,
+    PM_ERR_ARRAY_SEPARATOR,
+    PM_ERR_ARRAY_TERM,
+    PM_ERR_BEGIN_LONELY_ELSE,
+    PM_ERR_BEGIN_TERM,
+    PM_ERR_BEGIN_UPCASE_BRACE,
+    PM_ERR_BEGIN_UPCASE_TERM,
+    PM_ERR_BEGIN_UPCASE_TOPLEVEL,
+    PM_ERR_BLOCK_PARAM_LOCAL_VARIABLE,
+    PM_ERR_BLOCK_PARAM_PIPE_TERM,
+    PM_ERR_BLOCK_TERM_BRACE,
+    PM_ERR_BLOCK_TERM_END,
+    PM_ERR_CANNOT_PARSE_EXPRESSION,
+    PM_ERR_CANNOT_PARSE_STRING_PART,
+    PM_ERR_CASE_EXPRESSION_AFTER_CASE,
+    PM_ERR_CASE_EXPRESSION_AFTER_WHEN,
+    PM_ERR_CASE_MATCH_MISSING_PREDICATE,
+    PM_ERR_CASE_MISSING_CONDITIONS,
+    PM_ERR_CASE_TERM,
+    PM_ERR_CLASS_IN_METHOD,
+    PM_ERR_CLASS_NAME,
+    PM_ERR_CLASS_SUPERCLASS,
+    PM_ERR_CLASS_TERM,
+    PM_ERR_CLASS_UNEXPECTED_END,
+    PM_ERR_CLASS_VARIABLE_BARE,
+    PM_ERR_CONDITIONAL_ELSIF_PREDICATE,
+    PM_ERR_CONDITIONAL_IF_PREDICATE,
+    PM_ERR_CONDITIONAL_PREDICATE_TERM,
+    PM_ERR_CONDITIONAL_TERM,
+    PM_ERR_CONDITIONAL_TERM_ELSE,
+    PM_ERR_CONDITIONAL_UNLESS_PREDICATE,
+    PM_ERR_CONDITIONAL_UNTIL_PREDICATE,
+    PM_ERR_CONDITIONAL_WHILE_PREDICATE,
+    PM_ERR_CONSTANT_PATH_COLON_COLON_CONSTANT,
+    PM_ERR_DEF_ENDLESS,
+    PM_ERR_DEF_ENDLESS_PARAMETERS,
+    PM_ERR_DEF_ENDLESS_SETTER,
+    PM_ERR_DEF_ENDLESS_DO_BLOCK,
+    PM_ERR_DEF_NAME,
+    PM_ERR_DEF_PARAMS_TERM,
+    PM_ERR_DEF_PARAMS_TERM_PAREN,
+    PM_ERR_DEF_RECEIVER,
+    PM_ERR_DEF_RECEIVER_TERM,
+    PM_ERR_DEF_TERM,
+    PM_ERR_DEFINED_EXPRESSION,
+    PM_ERR_EMBDOC_TERM,
+    PM_ERR_EMBEXPR_END,
+    PM_ERR_EMBVAR_INVALID,
+    PM_ERR_END_UPCASE_BRACE,
+    PM_ERR_END_UPCASE_TERM,
+    PM_ERR_ESCAPE_INVALID_CONTROL,
+    PM_ERR_ESCAPE_INVALID_CONTROL_REPEAT,
+    PM_ERR_ESCAPE_INVALID_HEXADECIMAL,
+    PM_ERR_ESCAPE_INVALID_META,
+    PM_ERR_ESCAPE_INVALID_META_REPEAT,
+    PM_ERR_ESCAPE_INVALID_UNICODE,
+    PM_ERR_ESCAPE_INVALID_UNICODE_CM_FLAGS,
+    PM_ERR_ESCAPE_INVALID_UNICODE_LIST,
+    PM_ERR_ESCAPE_INVALID_UNICODE_LITERAL,
+    PM_ERR_ESCAPE_INVALID_UNICODE_LONG,
+    PM_ERR_ESCAPE_INVALID_UNICODE_SHORT,
+    PM_ERR_ESCAPE_INVALID_UNICODE_TERM,
+    PM_ERR_EXPECT_ARGUMENT,
+    PM_ERR_EXPECT_EOL_AFTER_STATEMENT,
+    PM_ERR_EXPECT_EXPRESSION_AFTER_AMPAMPEQ,
+    PM_ERR_EXPECT_EXPRESSION_AFTER_COMMA,
+    PM_ERR_EXPECT_EXPRESSION_AFTER_EQUAL,
+    PM_ERR_EXPECT_EXPRESSION_AFTER_LESS_LESS,
+    PM_ERR_EXPECT_EXPRESSION_AFTER_LPAREN,
+    PM_ERR_EXPECT_EXPRESSION_AFTER_OPERATOR,
+    PM_ERR_EXPECT_EXPRESSION_AFTER_PIPEPIPEEQ,
+    PM_ERR_EXPECT_EXPRESSION_AFTER_SPLAT,
+    PM_ERR_EXPECT_EXPRESSION_AFTER_SPLAT_HASH,
+    PM_ERR_EXPECT_EXPRESSION_AFTER_STAR,
+    PM_ERR_EXPECT_FOR_DELIMITER,
+    PM_ERR_EXPECT_IDENT_REQ_PARAMETER,
+    PM_ERR_EXPECT_IN_DELIMITER,
+    PM_ERR_EXPECT_LPAREN_AFTER_NOT_LPAREN,
+    PM_ERR_EXPECT_LPAREN_AFTER_NOT_OTHER,
+    PM_ERR_EXPECT_LPAREN_REQ_PARAMETER,
+    PM_ERR_EXPECT_MESSAGE,
+    PM_ERR_EXPECT_RBRACKET,
+    PM_ERR_EXPECT_RPAREN,
+    PM_ERR_EXPECT_RPAREN_AFTER_MULTI,
+    PM_ERR_EXPECT_RPAREN_REQ_PARAMETER,
+    PM_ERR_EXPECT_SINGLETON_CLASS_DELIMITER,
+    PM_ERR_EXPECT_STRING_CONTENT,
+    PM_ERR_EXPECT_WHEN_DELIMITER,
+    PM_ERR_EXPRESSION_BARE_HASH,
+    PM_ERR_EXPRESSION_NOT_WRITABLE,
+    PM_ERR_EXPRESSION_NOT_WRITABLE_ENCODING,
+    PM_ERR_EXPRESSION_NOT_WRITABLE_FALSE,
+    PM_ERR_EXPRESSION_NOT_WRITABLE_FILE,
+    PM_ERR_EXPRESSION_NOT_WRITABLE_LINE,
+    PM_ERR_EXPRESSION_NOT_WRITABLE_NIL,
+    PM_ERR_EXPRESSION_NOT_WRITABLE_NUMBERED,
+    PM_ERR_EXPRESSION_NOT_WRITABLE_SELF,
+    PM_ERR_EXPRESSION_NOT_WRITABLE_TRUE,
+    PM_ERR_FLOAT_PARSE,
+    PM_ERR_FOR_COLLECTION,
+    PM_ERR_FOR_IN,
+    PM_ERR_FOR_INDEX,
+    PM_ERR_FOR_TERM,
+    PM_ERR_GLOBAL_VARIABLE_BARE,
+    PM_ERR_HASH_EXPRESSION_AFTER_LABEL,
+    PM_ERR_HASH_KEY,
+    PM_ERR_HASH_ROCKET,
+    PM_ERR_HASH_TERM,
+    PM_ERR_HASH_VALUE,
+    PM_ERR_HEREDOC_IDENTIFIER,
+    PM_ERR_HEREDOC_TERM,
+    PM_ERR_INCOMPLETE_QUESTION_MARK,
+    PM_ERR_INCOMPLETE_VARIABLE_CLASS,
+    PM_ERR_INCOMPLETE_VARIABLE_CLASS_3_3,
+    PM_ERR_INCOMPLETE_VARIABLE_INSTANCE,
+    PM_ERR_INCOMPLETE_VARIABLE_INSTANCE_3_3,
+    PM_ERR_INSTANCE_VARIABLE_BARE,
+    PM_ERR_INVALID_BLOCK_EXIT,
+    PM_ERR_INVALID_CHARACTER,
+    PM_ERR_INVALID_COMMA,
+    PM_ERR_INVALID_ENCODING_MAGIC_COMMENT,
+    PM_ERR_INVALID_ESCAPE_CHARACTER,
+    PM_ERR_INVALID_FLOAT_EXPONENT,
+    PM_ERR_INVALID_LOCAL_VARIABLE_READ,
+    PM_ERR_INVALID_LOCAL_VARIABLE_WRITE,
+    PM_ERR_INVALID_MULTIBYTE_CHAR,
+    PM_ERR_INVALID_MULTIBYTE_CHARACTER,
+    PM_ERR_INVALID_MULTIBYTE_ESCAPE,
+    PM_ERR_INVALID_NUMBER_BINARY,
+    PM_ERR_INVALID_NUMBER_DECIMAL,
+    PM_ERR_INVALID_NUMBER_FRACTION,
+    PM_ERR_INVALID_NUMBER_HEXADECIMAL,
+    PM_ERR_INVALID_NUMBER_OCTAL,
+    PM_ERR_INVALID_NUMBER_UNDERSCORE_INNER,
+    PM_ERR_INVALID_NUMBER_UNDERSCORE_TRAILING,
+    PM_ERR_INVALID_PERCENT,
+    PM_ERR_INVALID_PERCENT_EOF,
+    PM_ERR_INVALID_PRINTABLE_CHARACTER,
+    PM_ERR_INVALID_RETRY_AFTER_ELSE,
+    PM_ERR_INVALID_RETRY_AFTER_ENSURE,
+    PM_ERR_INVALID_RETRY_WITHOUT_RESCUE,
+    PM_ERR_INVALID_SYMBOL,
+    PM_ERR_INVALID_VARIABLE_GLOBAL,
+    PM_ERR_INVALID_VARIABLE_GLOBAL_3_3,
+    PM_ERR_INVALID_YIELD,
+    PM_ERR_IT_NOT_ALLOWED_NUMBERED,
+    PM_ERR_IT_NOT_ALLOWED_ORDINARY,
+    PM_ERR_LAMBDA_OPEN,
+    PM_ERR_LAMBDA_TERM_BRACE,
+    PM_ERR_LAMBDA_TERM_END,
+    PM_ERR_LIST_I_LOWER_ELEMENT,
+    PM_ERR_LIST_I_LOWER_TERM,
+    PM_ERR_LIST_I_UPPER_ELEMENT,
+    PM_ERR_LIST_I_UPPER_TERM,
+    PM_ERR_LIST_W_LOWER_ELEMENT,
+    PM_ERR_LIST_W_LOWER_TERM,
+    PM_ERR_LIST_W_UPPER_ELEMENT,
+    PM_ERR_LIST_W_UPPER_TERM,
+    PM_ERR_MALLOC_FAILED,
+    PM_ERR_MIXED_ENCODING,
+    PM_ERR_MODULE_IN_METHOD,
+    PM_ERR_MODULE_NAME,
+    PM_ERR_MODULE_TERM,
+    PM_ERR_MULTI_ASSIGN_MULTI_SPLATS,
+    PM_ERR_MULTI_ASSIGN_UNEXPECTED_REST,
+    PM_ERR_NESTING_TOO_DEEP,
+    PM_ERR_NO_LOCAL_VARIABLE,
+    PM_ERR_NON_ASSOCIATIVE_OPERATOR,
+    PM_ERR_NOT_EXPRESSION,
+    PM_ERR_NUMBER_LITERAL_UNDERSCORE,
+    PM_ERR_NUMBERED_PARAMETER_INNER_BLOCK,
+    PM_ERR_NUMBERED_PARAMETER_IT,
+    PM_ERR_NUMBERED_PARAMETER_ORDINARY,
+    PM_ERR_NUMBERED_PARAMETER_OUTER_BLOCK,
+    PM_ERR_OPERATOR_MULTI_ASSIGN,
+    PM_ERR_OPERATOR_WRITE_ARGUMENTS,
+    PM_ERR_OPERATOR_WRITE_BLOCK,
+    PM_ERR_PARAMETER_ASSOC_SPLAT_MULTI,
+    PM_ERR_PARAMETER_BLOCK_MULTI,
+    PM_ERR_PARAMETER_CIRCULAR,
+    PM_ERR_PARAMETER_FORWARDING_AFTER_REST,
+    PM_ERR_PARAMETER_METHOD_NAME,
+    PM_ERR_PARAMETER_NAME_DUPLICATED,
+    PM_ERR_PARAMETER_NO_DEFAULT,
+    PM_ERR_PARAMETER_NO_DEFAULT_KW,
+    PM_ERR_PARAMETER_NUMBERED_RESERVED,
+    PM_ERR_PARAMETER_ORDER,
+    PM_ERR_PARAMETER_SPLAT_MULTI,
+    PM_ERR_PARAMETER_STAR,
+    PM_ERR_PARAMETER_UNEXPECTED_FWD,
+    PM_ERR_PARAMETER_UNEXPECTED_NO_KW,
+    PM_ERR_PARAMETER_WILD_LOOSE_COMMA,
+    PM_ERR_PATTERN_ARRAY_MULTIPLE_RESTS,
+    PM_ERR_PATTERN_CAPTURE_DUPLICATE,
+    PM_ERR_PATTERN_CAPTURE_IN_ALTERNATIVE,
+    PM_ERR_PATTERN_EXPRESSION_AFTER_BRACKET,
+    PM_ERR_PATTERN_EXPRESSION_AFTER_COMMA,
+    PM_ERR_PATTERN_EXPRESSION_AFTER_HROCKET,
+    PM_ERR_PATTERN_EXPRESSION_AFTER_IN,
+    PM_ERR_PATTERN_EXPRESSION_AFTER_KEY,
+    PM_ERR_PATTERN_EXPRESSION_AFTER_PAREN,
+    PM_ERR_PATTERN_EXPRESSION_AFTER_PIN,
+    PM_ERR_PATTERN_EXPRESSION_AFTER_PIPE,
+    PM_ERR_PATTERN_EXPRESSION_AFTER_RANGE,
+    PM_ERR_PATTERN_EXPRESSION_AFTER_REST,
+    PM_ERR_PATTERN_FIND_MISSING_INNER,
+    PM_ERR_PATTERN_HASH_IMPLICIT,
+    PM_ERR_PATTERN_HASH_KEY,
+    PM_ERR_PATTERN_HASH_KEY_DUPLICATE,
+    PM_ERR_PATTERN_HASH_KEY_INTERPOLATED,
+    PM_ERR_PATTERN_HASH_KEY_LABEL,
+    PM_ERR_PATTERN_HASH_KEY_LOCALS,
+    PM_ERR_PATTERN_IDENT_AFTER_HROCKET,
+    PM_ERR_PATTERN_LABEL_AFTER_COMMA,
+    PM_ERR_PATTERN_REST,
+    PM_ERR_PATTERN_TERM_BRACE,
+    PM_ERR_PATTERN_TERM_BRACKET,
+    PM_ERR_PATTERN_TERM_PAREN,
+    PM_ERR_PIPEPIPEEQ_MULTI_ASSIGN,
+    PM_ERR_REGEXP_ENCODING_OPTION_MISMATCH,
+    PM_ERR_REGEXP_ESCAPED_NON_ASCII_IN_UTF8,
+    PM_ERR_REGEXP_INCOMPAT_CHAR_ENCODING,
+    PM_ERR_REGEXP_INVALID_CHAR_PROPERTY,
+    PM_ERR_REGEXP_INVALID_UNICODE_RANGE,
+    PM_ERR_REGEXP_NON_ESCAPED_MBC,
+    PM_ERR_REGEXP_PARSE_ERROR,
+    PM_ERR_REGEXP_TERM,
+    PM_ERR_REGEXP_UNKNOWN_OPTIONS,
+    PM_ERR_REGEXP_UTF8_CHAR_NON_UTF8_REGEXP,
+    PM_ERR_RESCUE_EXPRESSION,
+    PM_ERR_RESCUE_MODIFIER_VALUE,
+    PM_ERR_RESCUE_TERM,
+    PM_ERR_RESCUE_VARIABLE,
+    PM_ERR_RETURN_INVALID,
+    PM_ERR_SCRIPT_NOT_FOUND,
+    PM_ERR_SINGLETON_FOR_LITERALS,
+    PM_ERR_STATEMENT_ALIAS,
+    PM_ERR_STATEMENT_POSTEXE_END,
+    PM_ERR_STATEMENT_PREEXE_BEGIN,
+    PM_ERR_STATEMENT_UNDEF,
+    PM_ERR_STRING_CONCATENATION,
+    PM_ERR_STRING_INTERPOLATED_TERM,
+    PM_ERR_STRING_LITERAL_EOF,
+    PM_ERR_STRING_LITERAL_TERM,
+    PM_ERR_SYMBOL_INVALID,
+    PM_ERR_SYMBOL_TERM_DYNAMIC,
+    PM_ERR_SYMBOL_TERM_INTERPOLATED,
+    PM_ERR_TERNARY_COLON,
+    PM_ERR_TERNARY_EXPRESSION_FALSE,
+    PM_ERR_TERNARY_EXPRESSION_TRUE,
+    PM_ERR_UNARY_DISALLOWED,
+    PM_ERR_UNARY_RECEIVER,
+    PM_ERR_UNDEF_ARGUMENT,
+    PM_ERR_UNEXPECTED_BLOCK_ARGUMENT,
+    PM_ERR_UNEXPECTED_INDEX_BLOCK,
+    PM_ERR_UNEXPECTED_INDEX_KEYWORDS,
+    PM_ERR_UNEXPECTED_LABEL,
+    PM_ERR_UNEXPECTED_MULTI_WRITE,
+    PM_ERR_UNEXPECTED_PARAMETER_DEFAULT_VALUE,
+    PM_ERR_UNEXPECTED_RANGE_OPERATOR,
+    PM_ERR_UNEXPECTED_SAFE_NAVIGATION,
+    PM_ERR_UNEXPECTED_TOKEN_CLOSE_CONTEXT,
+    PM_ERR_UNEXPECTED_TOKEN_IGNORE,
+    PM_ERR_UNTIL_TERM,
+    PM_ERR_VOID_EXPRESSION,
+    PM_ERR_WHILE_TERM,
+    PM_ERR_WRITE_TARGET_IN_METHOD,
+    PM_ERR_WRITE_TARGET_READONLY,
+    PM_ERR_WRITE_TARGET_UNEXPECTED,
+    PM_ERR_XSTRING_TERM,
+
+    /* These are the warning diagnostics. */
+    PM_WARN_AMBIGUOUS_BINARY_OPERATOR,
+    PM_WARN_AMBIGUOUS_FIRST_ARGUMENT_MINUS,
+    PM_WARN_AMBIGUOUS_FIRST_ARGUMENT_PLUS,
+    PM_WARN_AMBIGUOUS_PREFIX_AMPERSAND,
+    PM_WARN_AMBIGUOUS_PREFIX_STAR,
+    PM_WARN_AMBIGUOUS_PREFIX_STAR_STAR,
+    PM_WARN_AMBIGUOUS_SLASH,
+    PM_WARN_COMPARISON_AFTER_COMPARISON,
+    PM_WARN_DOT_DOT_DOT_EOL,
+    PM_WARN_EQUAL_IN_CONDITIONAL,
+    PM_WARN_EQUAL_IN_CONDITIONAL_3_3,
+    PM_WARN_END_IN_METHOD,
+    PM_WARN_DUPLICATED_HASH_KEY,
+    PM_WARN_DUPLICATED_WHEN_CLAUSE,
+    PM_WARN_FLOAT_OUT_OF_RANGE,
+    PM_WARN_IGNORED_FROZEN_STRING_LITERAL,
+    PM_WARN_INDENTATION_MISMATCH,
+    PM_WARN_INTEGER_IN_FLIP_FLOP,
+    PM_WARN_INVALID_CHARACTER,
+    PM_WARN_INVALID_MAGIC_COMMENT_VALUE,
+    PM_WARN_INVALID_NUMBERED_REFERENCE,
+    PM_WARN_KEYWORD_EOL,
+    PM_WARN_LITERAL_IN_CONDITION_DEFAULT,
+    PM_WARN_LITERAL_IN_CONDITION_VERBOSE,
+    PM_WARN_SHAREABLE_CONSTANT_VALUE_LINE,
+    PM_WARN_SHEBANG_CARRIAGE_RETURN,
+    PM_WARN_UNEXPECTED_CARRIAGE_RETURN,
+    PM_WARN_UNREACHABLE_STATEMENT,
+    PM_WARN_UNUSED_LOCAL_VARIABLE,
+    PM_WARN_VOID_STATEMENT,
+} pm_diagnostic_id_t;
+
+/*
+ * This struct represents a diagnostic generated during parsing.
+ */
+struct pm_diagnostic_t {
+    /* The embedded base node. */
+    pm_list_node_t node;
+
+    /* The location of the diagnostic in the source. */
+    pm_location_t location;
+
+    /* The ID of the diagnostic. */
+    pm_diagnostic_id_t diag_id;
+
+    /* The message associated with the diagnostic. */
+    const char *message;
+
+    /*
+     * The level of the diagnostic, see `pm_error_level_t` and
+     * `pm_warning_level_t` for possible values.
+     */
+    uint8_t level;
+};
+
+/*
+ * Append a diagnostic to the given list of diagnostics that is using shared
+ * memory for its message.
+ */
+void pm_diagnostic_list_append(pm_arena_t *arena, pm_list_t *list, uint32_t start, uint32_t length, pm_diagnostic_id_t diag_id);
+
+/*
+ * Append a diagnostic to the given list of diagnostics that is using a format
+ * string for its message.
+ */
+void pm_diagnostic_list_append_format(pm_arena_t *arena, pm_list_t *list, uint32_t start, uint32_t length, pm_diagnostic_id_t diag_id, ...);
+
+#endif

data/include/prism/internal/encoding.h

@@ -0,0 +1,242 @@
+#ifndef PRISM_INTERNAL_ENCODING_H
+#define PRISM_INTERNAL_ENCODING_H
+
+#include <stdbool.h>
+#include <stddef.h>
+#include <stdint.h>
+
+/*
+ * This struct defines the functions necessary to implement the encoding
+ * interface so we can determine how many bytes the subsequent character takes.
+ * Each callback should return the number of bytes, or 0 if the next bytes are
+ * invalid for the encoding and type.
+ */
+typedef struct {
+    /*
+     * Return the number of bytes that the next character takes if it is valid
+     * in the encoding. Does not read more than n bytes. It is assumed that n is
+     * at least 1.
+     */
+    size_t (*char_width)(const uint8_t *b, ptrdiff_t n);
+
+    /*
+     * Return the number of bytes that the next character takes if it is valid
+     * in the encoding and is alphabetical. Does not read more than n bytes. It
+     * is assumed that n is at least 1.
+     */
+    size_t (*alpha_char)(const uint8_t *b, ptrdiff_t n);
+
+    /*
+     * Return the number of bytes that the next character takes if it is valid
+     * in the encoding and is alphanumeric. Does not read more than n bytes. It
+     * is assumed that n is at least 1.
+     */
+    size_t (*alnum_char)(const uint8_t *b, ptrdiff_t n);
+
+    /*
+     * Return true if the next character is valid in the encoding and is an
+     * uppercase character. Does not read more than n bytes. It is assumed that
+     * n is at least 1.
+     */
+    bool (*isupper_char)(const uint8_t *b, ptrdiff_t n);
+
+    /*
+     * The name of the encoding. This should correspond to a value that can be
+     * passed to Encoding.find in Ruby.
+     */
+    const char *name;
+
+    /* Return true if the encoding is a multibyte encoding. */
+    bool multibyte;
+} pm_encoding_t;
+
+/*
+ * All of the lookup tables use the first bit of each embedded byte to indicate
+ * whether the codepoint is alphabetical.
+ */
+#define PRISM_ENCODING_ALPHABETIC_BIT 1 << 0
+
+/*
+ * All of the lookup tables use the second bit of each embedded byte to indicate
+ * whether the codepoint is alphanumeric.
+ */
+#define PRISM_ENCODING_ALPHANUMERIC_BIT 1 << 1
+
+/*
+ * All of the lookup tables use the third bit of each embedded byte to indicate
+ * whether the codepoint is uppercase.
+ */
+#define PRISM_ENCODING_UPPERCASE_BIT 1 << 2
+
+/* Return the size of the next character in the UTF-8 encoding. */
+size_t pm_encoding_utf_8_char_width(const uint8_t *b, ptrdiff_t n);
+
+/*
+ * Return the size of the next character in the UTF-8 encoding if it is an
+ * alphabetical character.
+ */
+size_t pm_encoding_utf_8_alpha_char(const uint8_t *b, ptrdiff_t n);
+
+/*
+ * Return the size of the next character in the UTF-8 encoding if it is an
+ * alphanumeric character.
+ */
+size_t pm_encoding_utf_8_alnum_char(const uint8_t *b, ptrdiff_t n);
+
+/*
+ * Return true if the next character in the UTF-8 encoding if it is an uppercase
+ * character.
+ */
+bool pm_encoding_utf_8_isupper_char(const uint8_t *b, ptrdiff_t n);
+
+/*
+ * This lookup table is referenced in both the UTF-8 encoding file and the
+ * parser directly in order to speed up the default encoding processing. It is
+ * used to indicate whether a character is alphabetical, alphanumeric, or
+ * uppercase in unicode mappings.
+ */
+extern const uint8_t pm_encoding_unicode_table[256];
+
+/* These are all of the encodings that prism supports. */
+typedef enum {
+    PM_ENCODING_UTF_8 = 0,
+    PM_ENCODING_US_ASCII,
+    PM_ENCODING_ASCII_8BIT,
+    PM_ENCODING_EUC_JP,
+    PM_ENCODING_WINDOWS_31J,
+
+/* We optionally support excluding the full set of encodings to only support the
+ * minimum necessary to process Ruby code without encoding comments. */
+#ifndef PRISM_ENCODING_EXCLUDE_FULL
+    PM_ENCODING_BIG5,
+    PM_ENCODING_BIG5_HKSCS,
+    PM_ENCODING_BIG5_UAO,
+    PM_ENCODING_CESU_8,
+    PM_ENCODING_CP51932,
+    PM_ENCODING_CP850,
+    PM_ENCODING_CP852,
+    PM_ENCODING_CP855,
+    PM_ENCODING_CP949,
+    PM_ENCODING_CP950,
+    PM_ENCODING_CP951,
+    PM_ENCODING_EMACS_MULE,
+    PM_ENCODING_EUC_JP_MS,
+    PM_ENCODING_EUC_JIS_2004,
+    PM_ENCODING_EUC_KR,
+    PM_ENCODING_EUC_TW,
+    PM_ENCODING_GB12345,
+    PM_ENCODING_GB18030,
+    PM_ENCODING_GB1988,
+    PM_ENCODING_GB2312,
+    PM_ENCODING_GBK,
+    PM_ENCODING_IBM437,
+    PM_ENCODING_IBM720,
+    PM_ENCODING_IBM737,
+    PM_ENCODING_IBM775,
+    PM_ENCODING_IBM852,
+    PM_ENCODING_IBM855,
+    PM_ENCODING_IBM857,
+    PM_ENCODING_IBM860,
+    PM_ENCODING_IBM861,
+    PM_ENCODING_IBM862,
+    PM_ENCODING_IBM863,
+    PM_ENCODING_IBM864,
+    PM_ENCODING_IBM865,
+    PM_ENCODING_IBM866,
+    PM_ENCODING_IBM869,
+    PM_ENCODING_ISO_8859_1,
+    PM_ENCODING_ISO_8859_2,
+    PM_ENCODING_ISO_8859_3,
+    PM_ENCODING_ISO_8859_4,
+    PM_ENCODING_ISO_8859_5,
+    PM_ENCODING_ISO_8859_6,
+    PM_ENCODING_ISO_8859_7,
+    PM_ENCODING_ISO_8859_8,
+    PM_ENCODING_ISO_8859_9,
+    PM_ENCODING_ISO_8859_10,
+    PM_ENCODING_ISO_8859_11,
+    PM_ENCODING_ISO_8859_13,
+    PM_ENCODING_ISO_8859_14,
+    PM_ENCODING_ISO_8859_15,
+    PM_ENCODING_ISO_8859_16,
+    PM_ENCODING_KOI8_R,
+    PM_ENCODING_KOI8_U,
+    PM_ENCODING_MAC_CENT_EURO,
+    PM_ENCODING_MAC_CROATIAN,
+    PM_ENCODING_MAC_CYRILLIC,
+    PM_ENCODING_MAC_GREEK,
+    PM_ENCODING_MAC_ICELAND,
+    PM_ENCODING_MAC_JAPANESE,
+    PM_ENCODING_MAC_ROMAN,
+    PM_ENCODING_MAC_ROMANIA,
+    PM_ENCODING_MAC_THAI,
+    PM_ENCODING_MAC_TURKISH,
+    PM_ENCODING_MAC_UKRAINE,
+    PM_ENCODING_SHIFT_JIS,
+    PM_ENCODING_SJIS_DOCOMO,
+    PM_ENCODING_SJIS_KDDI,
+    PM_ENCODING_SJIS_SOFTBANK,
+    PM_ENCODING_STATELESS_ISO_2022_JP,
+    PM_ENCODING_STATELESS_ISO_2022_JP_KDDI,
+    PM_ENCODING_TIS_620,
+    PM_ENCODING_UTF8_MAC,
+    PM_ENCODING_UTF8_DOCOMO,
+    PM_ENCODING_UTF8_KDDI,
+    PM_ENCODING_UTF8_SOFTBANK,
+    PM_ENCODING_WINDOWS_1250,
+    PM_ENCODING_WINDOWS_1251,
+    PM_ENCODING_WINDOWS_1252,
+    PM_ENCODING_WINDOWS_1253,
+    PM_ENCODING_WINDOWS_1254,
+    PM_ENCODING_WINDOWS_1255,
+    PM_ENCODING_WINDOWS_1256,
+    PM_ENCODING_WINDOWS_1257,
+    PM_ENCODING_WINDOWS_1258,
+    PM_ENCODING_WINDOWS_874,
+#endif
+
+    PM_ENCODING_MAXIMUM
+} pm_encoding_type_t;
+
+/* This is the table of all of the encodings that prism supports. */
+extern const pm_encoding_t pm_encodings[PM_ENCODING_MAXIMUM];
+
+/*
+ * This is the default UTF-8 encoding. We need a reference to it to quickly
+ * create parsers.
+ */
+#define PM_ENCODING_UTF_8_ENTRY (&pm_encodings[PM_ENCODING_UTF_8])
+
+/*
+ * This is the US-ASCII encoding. We need a reference to it to be able to
+ * compare against it when a string is being created because it could possibly
+ * need to fall back to ASCII-8BIT.
+ */
+#define PM_ENCODING_US_ASCII_ENTRY (&pm_encodings[PM_ENCODING_US_ASCII])
+
+/*
+ * This is the ASCII-8BIT encoding. We need a reference to it so that pm_strpbrk
+ * can compare against it because invalid multibyte characters are not a thing
+ * in this encoding. It is also needed for handling Regexp encoding flags.
+ */
+#define PM_ENCODING_ASCII_8BIT_ENTRY (&pm_encodings[PM_ENCODING_ASCII_8BIT])
+
+/*
+ * This is the EUC-JP encoding. We need a reference to it to quickly process
+ * regular expression modifiers.
+ */
+#define PM_ENCODING_EUC_JP_ENTRY (&pm_encodings[PM_ENCODING_EUC_JP])
+
+/*
+ * This is the Windows-31J encoding. We need a reference to it to quickly
+ * process regular expression modifiers.
+ */
+#define PM_ENCODING_WINDOWS_31J_ENTRY (&pm_encodings[PM_ENCODING_WINDOWS_31J])
+
+/*
+ * Parse the given name of an encoding and return a pointer to the corresponding
+ * encoding struct if one can be found, otherwise return NULL.
+ */
+const pm_encoding_t * pm_encoding_find(const uint8_t *start, const uint8_t *end);
+
+#endif

data/include/prism/internal/integer.h

@@ -0,0 +1,68 @@
+/*
+ * This module provides functions for working with arbitrary-sized integers.
+ */
+#ifndef PRISM_INTERNAL_INTEGER_H
+#define PRISM_INTERNAL_INTEGER_H
+
+#include "prism/buffer.h"
+#include "prism/integer.h"
+
+#include <stdint.h>
+
+/*
+ * An enum controlling the base of an integer. It is expected that the base is
+ * already known before parsing the integer, even though it could be derived
+ * from the string itself.
+ */
+typedef enum {
+    /* The default decimal base, with no prefix. Leading 0s will be ignored. */
+    PM_INTEGER_BASE_DEFAULT,
+
+    /* The binary base, indicated by a 0b or 0B prefix. */
+    PM_INTEGER_BASE_BINARY,
+
+    /* The octal base, indicated by a 0, 0o, or 0O prefix. */
+    PM_INTEGER_BASE_OCTAL,
+
+    /* The decimal base, indicated by a 0d, 0D, or empty prefix. */
+    PM_INTEGER_BASE_DECIMAL,
+
+    /* The hexadecimal base, indicated by a 0x or 0X prefix. */
+    PM_INTEGER_BASE_HEXADECIMAL,
+
+    /*
+     * An unknown base, in which case pm_integer_parse will derive it based on
+     * the content of the string. This is less efficient and does more
+     * comparisons, so if callers know the base ahead of time, they should use
+     * that instead.
+     */
+    PM_INTEGER_BASE_UNKNOWN
+} pm_integer_base_t;
+
+/*
+ * Parse an integer from a string. This assumes that the format of the integer
+ * has already been validated, as internal validation checks are not performed
+ * here.
+ */
+void pm_integer_parse(pm_integer_t *integer, pm_integer_base_t base, const uint8_t *start, const uint8_t *end);
+
+/*
+ * Compare two integers. This function returns -1 if the left integer is less
+ * than the right integer, 0 if they are equal, and 1 if the left integer is
+ * greater than the right integer.
+ */
+int pm_integer_compare(const pm_integer_t *left, const pm_integer_t *right);
+
+/*
+ * Reduce a ratio of integers to its simplest form.
+ *
+ * If either the numerator or denominator do not fit into a 32-bit integer, then
+ * this function is a no-op. In the future, we may consider reducing even the
+ * larger numbers, but for now we're going to keep it simple.
+ */
+void pm_integers_reduce(pm_integer_t *numerator, pm_integer_t *denominator);
+
+/* Convert an integer to a decimal string. */
+void pm_integer_string(pm_buffer_t *buffer, const pm_integer_t *integer);
+
+#endif