debase-ruby_core_source 4.0.1 → 4.1.0.preview1

data/lib/debase/ruby_core_source/ruby-4.1.0-preview1/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/lib/debase/ruby_core_source/ruby-4.1.0-preview1/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

data/lib/debase/ruby_core_source/ruby-4.1.0-preview1/prism/internal/isinf.h

@@ -0,0 +1,16 @@
+#ifndef PRISM_INTERNAL_ISINF_H
+#define PRISM_INTERNAL_ISINF_H
+
+/*
+ * isinf on POSIX systems accepts a float, a double, or a long double. But mingw
+ * didn't provide an isinf macro, only an isinf function that only accepts
+ * floats, so we need to use _finite instead.
+ */
+#ifdef __MINGW64__
+    #include <float.h>
+    #define PRISM_ISINF(x) (!_finite(x))
+#else
+    #define PRISM_ISINF(x) isinf(x)
+#endif
+
+#endif

data/lib/debase/ruby_core_source/ruby-4.1.0-preview1/prism/internal/line_offset_list.h

@@ -0,0 +1,34 @@
+#ifndef PRISM_INTERNAL_LINE_OFFSET_LIST_H
+#define PRISM_INTERNAL_LINE_OFFSET_LIST_H
+
+#include "prism/compiler/force_inline.h"
+
+#include "prism/arena.h"
+#include "prism/line_offset_list.h"
+
+/* Initialize a new line offset list with the given capacity. */
+void pm_line_offset_list_init(pm_arena_t *arena, pm_line_offset_list_t *list, size_t capacity);
+
+/* Clear out the offsets that have been appended to the list. */
+void pm_line_offset_list_clear(pm_line_offset_list_t *list);
+
+/* Append a new offset to the list (slow path with resize). */
+void pm_line_offset_list_append_slow(pm_arena_t *arena, pm_line_offset_list_t *list, uint32_t cursor);
+
+/* Append a new offset to the list. */
+static PRISM_FORCE_INLINE void
+pm_line_offset_list_append(pm_arena_t *arena, pm_line_offset_list_t *list, uint32_t cursor) {
+    if (list->size < list->capacity) {
+        list->offsets[list->size++] = cursor;
+    } else {
+        pm_line_offset_list_append_slow(arena, list, cursor);
+    }
+}
+
+/*
+ * Returns the line of the given offset. If the offset is not in the list, the
+ * line of the closest offset less than the given offset is returned.
+ */
+int32_t pm_line_offset_list_line(const pm_line_offset_list_t *list, uint32_t cursor, int32_t start_line);
+
+#endif

data/lib/debase/ruby_core_source/ruby-4.1.0-preview1/prism/internal/list.h

@@ -0,0 +1,62 @@
+#ifndef PRISM_INTERNAL_LIST_H
+#define PRISM_INTERNAL_LIST_H
+
+#include <stddef.h>
+
+/*
+ * This struct represents an abstract linked list that provides common
+ * functionality. It is meant to be used any time a linked list is necessary to
+ * store data.
+ *
+ * The linked list itself operates off a set of pointers. Because the pointers
+ * are not necessarily sequential, they can be of any size. We use this fact to
+ * allow the consumer of this linked list to extend the node struct to include
+ * any data they want. This is done by using the pm_list_node_t as the first
+ * member of the struct.
+ *
+ * For example, if we want to store a list of integers, we can do the following:
+ *
+ * ```c
+ * typedef struct {
+ *     pm_list_node_t node;
+ *     int value;
+ * } pm_int_node_t;
+ *
+ * pm_list_t list = { 0 };
+ * pm_int_node_t *node = xmalloc(sizeof(pm_int_node_t));
+ * node->value = 5;
+ *
+ * pm_list_append(&list, &node->node);
+ * ```
+ *
+ * The pm_list_t struct is used to represent the overall linked list. It
+ * contains a pointer to the head and tail of the list. This allows for easy
+ * iteration and appending of new nodes.
+ */
+typedef struct pm_list_node {
+    /* A pointer to the next node in the list. */
+    struct pm_list_node *next;
+} pm_list_node_t;
+
+/*
+ * This represents the overall linked list. It keeps a pointer to the head and
+ * tail so that iteration is easy and pushing new nodes is easy.
+ */
+typedef struct {
+    /* The size of the list. */
+    size_t size;
+
+    /* A pointer to the head of the list. */
+    pm_list_node_t *head;
+
+    /* A pointer to the tail of the list. */
+    pm_list_node_t *tail;
+} pm_list_t;
+
+/* Returns the size of the list. */
+size_t pm_list_size(pm_list_t *list);
+
+/* Append a node to the given list. */
+void pm_list_append(pm_list_t *list, pm_list_node_t *node);
+
+#endif

data/lib/debase/ruby_core_source/ruby-4.1.0-preview1/prism/internal/magic_comments.h

@@ -0,0 +1,23 @@
+#ifndef PRISM_INTERNAL_MAGIC_COMMENTS_H
+#define PRISM_INTERNAL_MAGIC_COMMENTS_H
+
+#include "prism/magic_comments.h"
+
+#include "prism/internal/list.h"
+
+/*
+ * This is a node in the linked list of magic comments that we've found while
+ * parsing.
+ */
+struct pm_magic_comment_t {
+    /* The embedded base node. */
+    pm_list_node_t node;
+
+    /* The key of the magic comment. */
+    pm_location_t key;
+
+    /* The value of the magic comment. */
+    pm_location_t value;
+};
+
+#endif

data/lib/debase/ruby_core_source/ruby-4.1.0-preview1/prism/internal/memchr.h

@@ -0,0 +1,15 @@
+#ifndef PRISM_INTERNAL_MEMCHR_H
+#define PRISM_INTERNAL_MEMCHR_H
+
+#include "prism/internal/encoding.h"
+
+#include <stddef.h>
+
+/*
+ * We need to roll our own memchr to handle cases where the encoding changes and
+ * we need to search for a character in a buffer that could be the trailing byte
+ * of a multibyte character.
+ */
+const void * pm_memchr(const void *source, int character, size_t number, bool encoding_changed, const pm_encoding_t *encoding);
+
+#endif

data/lib/debase/ruby_core_source/ruby-4.1.0-preview1/prism/internal/node.h

@@ -0,0 +1,32 @@
+#ifndef PRISM_INTERNAL_NODE_H
+#define PRISM_INTERNAL_NODE_H
+
+#include "prism/node.h"
+
+#include "prism/compiler/force_inline.h"
+
+#include "prism/arena.h"
+
+/*
+ * Slow path for pm_node_list_append: grow the list and append the node.
+ * Do not call directly — use pm_node_list_append instead.
+ */
+void pm_node_list_append_slow(pm_arena_t *arena, pm_node_list_t *list, pm_node_t *node);
+
+/* Append a new node onto the end of the node list. */
+static PRISM_FORCE_INLINE void
+pm_node_list_append(pm_arena_t *arena, pm_node_list_t *list, pm_node_t *node) {
+    if (list->size < list->capacity) {
+        list->nodes[list->size++] = node;
+    } else {
+        pm_node_list_append_slow(arena, list, node);
+    }
+}
+
+/* Prepend a new node onto the beginning of the node list. */
+void pm_node_list_prepend(pm_arena_t *arena, pm_node_list_t *list, pm_node_t *node);
+
+/* Concatenate the given node list onto the end of the other node list. */
+void pm_node_list_concat(pm_arena_t *arena, pm_node_list_t *list, pm_node_list_t *other);
+
+#endif