/* Demangler for the D programming language
- Copyright (C) 2014-2017 Free Software Foundation, Inc.
+ Copyright (C) 2014-2021 Free Software Foundation, Inc.
Written by Iain Buclaw (ibuclaw@gdcproject.org)
This file is part of the libiberty library.
License along with libiberty; see the file COPYING.LIB.
If not, see <http://www.gnu.org/licenses/>. */
-/* This file exports one function; dlang_demangle.
-
- This file imports strtol for decoding mangled literals. */
+/* This file exports one function; dlang_demangle. */
#ifdef HAVE_CONFIG_H
#include "config.h"
#endif
+#ifdef HAVE_LIMITS_H
+#include <limits.h>
+#endif
#include "safe-ctype.h"
#ifdef HAVE_STDLIB_H
#include <stdlib.h>
-#else
-extern long strtol (const char *nptr, char **endptr, int base);
#endif
#include <demangle.h>
#include "libiberty.h"
+#ifndef ULONG_MAX
+#define ULONG_MAX (~0UL)
+#endif
+#ifndef UINT_MAX
+#define UINT_MAX (~0U)
+#endif
+
/* A mini string-handling package */
typedef struct string /* Beware: these aren't required to be */
} string;
static void
-string_need (string *s, int n)
+string_need (string *s, size_t n)
{
- int tem;
+ size_t tem;
if (s->b == NULL)
{
s->p = s->b = XNEWVEC (char, n);
s->e = s->b + n;
}
- else if (s->e - s->p < n)
+ else if ((size_t) (s->e - s->p) < n)
{
tem = s->p - s->b;
n += tem;
static void
string_append (string *p, const char *s)
{
- int n = strlen (s);
+ size_t n = strlen (s);
string_need (p, n);
memcpy (p->p, s, n);
p->p += n;
}
static void
-string_appendn (string *p, const char *s, int n)
+string_appendn (string *p, const char *s, size_t n)
{
if (n != 0)
{
}
static void
-string_prependn (string *p, const char *s, int n)
+string_prependn (string *p, const char *s, size_t n)
{
char *q;
}
}
-/* What kinds of symbol we could be parsing. */
-enum dlang_symbol_kinds
+/* Demangle information structure we pass around. */
+struct dlang_info
{
- /* Top-level symbol, needs it's type checked. */
- dlang_top_level,
- /* Function symbol, needs it's type checked. */
- dlang_function,
- /* Strongly typed name, such as for classes, structs and enums. */
- dlang_type_name,
- /* Template identifier. */
- dlang_template_ident,
- /* Template symbol parameter. */
- dlang_template_param
+ /* The string we are demangling. */
+ const char *s;
+ /* The index of the last back reference. */
+ int last_backref;
};
+/* Pass as the LEN to dlang_parse_template if symbol length is not known. */
+#define TEMPLATE_LENGTH_UNKNOWN (-1UL)
+
/* Prototypes for forward referenced functions */
-static const char *dlang_function_args (string *, const char *);
+static const char *dlang_function_type (string *, const char *,
+ struct dlang_info *);
-static const char *dlang_type (string *, const char *);
+static const char *dlang_function_args (string *, const char *,
+ struct dlang_info *);
+
+static const char *dlang_type (string *, const char *, struct dlang_info *);
static const char *dlang_value (string *, const char *, const char *, char);
-static const char *dlang_parse_symbol (string *, const char *,
- enum dlang_symbol_kinds);
+static const char *dlang_parse_qualified (string *, const char *,
+ struct dlang_info *, int);
+
+static const char *dlang_parse_mangle (string *, const char *,
+ struct dlang_info *);
+
+static const char *dlang_parse_tuple (string *, const char *,
+ struct dlang_info *);
+
+static const char *dlang_parse_template (string *, const char *,
+ struct dlang_info *, unsigned long);
+
+static const char *dlang_lname (string *, const char *, unsigned long);
+
+
+/* Extract the number from MANGLED, and assign the result to RET.
+ Return the remaining string on success or NULL on failure.
+ A result larger than UINT_MAX is considered a failure. */
+static const char *
+dlang_number (const char *mangled, unsigned long *ret)
+{
+ /* Return NULL if trying to extract something that isn't a digit. */
+ if (mangled == NULL || !ISDIGIT (*mangled))
+ return NULL;
+
+ unsigned long val = 0;
+
+ while (ISDIGIT (*mangled))
+ {
+ unsigned long digit = mangled[0] - '0';
+
+ /* Check for overflow. */
+ if (val > (UINT_MAX - digit) / 10)
+ return NULL;
+
+ val = val * 10 + digit;
+ mangled++;
+ }
+
+ if (*mangled == '\0')
+ return NULL;
+
+ *ret = val;
+ return mangled;
+}
+
+/* Extract the hex-digit from MANGLED, and assign the result to RET.
+ Return the remaining string on success or NULL on failure. */
+static const char *
+dlang_hexdigit (const char *mangled, char *ret)
+{
+ char c;
+
+ /* Return NULL if trying to extract something that isn't a hexdigit. */
+ if (mangled == NULL || !ISXDIGIT (mangled[0]) || !ISXDIGIT (mangled[1]))
+ return NULL;
+
+ c = mangled[0];
+ if (!ISDIGIT (c))
+ (*ret) = (c - (ISUPPER (c) ? 'A' : 'a') + 10);
+ else
+ (*ret) = (c - '0');
+
+ c = mangled[1];
+ if (!ISDIGIT (c))
+ (*ret) = (*ret << 4) | (c - (ISUPPER (c) ? 'A' : 'a') + 10);
+ else
+ (*ret) = (*ret << 4) | (c - '0');
+
+ mangled += 2;
+
+ return mangled;
+}
+
+/* Extract the function calling convention from MANGLED and
+ return 1 on success or 0 on failure. */
+static int
+dlang_call_convention_p (const char *mangled)
+{
+ switch (*mangled)
+ {
+ case 'F': case 'U': case 'V':
+ case 'W': case 'R': case 'Y':
+ return 1;
+
+ default:
+ return 0;
+ }
+}
+
+/* Extract the back reference position from MANGLED, and assign the result
+ to RET. Return the remaining string on success or NULL on failure.
+ A result <= 0 is a failure. */
+static const char *
+dlang_decode_backref (const char *mangled, long *ret)
+{
+ /* Return NULL if trying to extract something that isn't a digit. */
+ if (mangled == NULL || !ISALPHA (*mangled))
+ return NULL;
+
+ /* Any identifier or non-basic type that has been emitted to the mangled
+ symbol before will not be emitted again, but is referenced by a special
+ sequence encoding the relative position of the original occurrence in the
+ mangled symbol name.
+
+ Numbers in back references are encoded with base 26 by upper case letters
+ A-Z for higher digits but lower case letters a-z for the last digit.
+
+ NumberBackRef:
+ [a-z]
+ [A-Z] NumberBackRef
+ ^
+ */
+ unsigned long val = 0;
+
+ while (ISALPHA (*mangled))
+ {
+ /* Check for overflow. */
+ if (val > (ULONG_MAX - 25) / 26)
+ break;
+
+ val *= 26;
+
+ if (mangled[0] >= 'a' && mangled[0] <= 'z')
+ {
+ val += mangled[0] - 'a';
+ if ((long) val <= 0)
+ break;
+ *ret = val;
+ return mangled + 1;
+ }
+
+ val += mangled[0] - 'A';
+ mangled++;
+ }
+
+ return NULL;
+}
+
+/* Extract the symbol pointed at by the back reference and assign the result
+ to RET. Return the remaining string on success or NULL on failure. */
+static const char *
+dlang_backref (const char *mangled, const char **ret, struct dlang_info *info)
+{
+ (*ret) = NULL;
+
+ if (mangled == NULL || *mangled != 'Q')
+ return NULL;
+
+ /* Position of 'Q'. */
+ const char *qpos = mangled;
+ long refpos;
+ mangled++;
+
+ mangled = dlang_decode_backref (mangled, &refpos);
+ if (mangled == NULL)
+ return NULL;
+
+ if (refpos > qpos - info->s)
+ return NULL;
+
+ /* Set the position of the back reference. */
+ (*ret) = qpos - refpos;
+
+ return mangled;
+}
+
+/* Demangle a back referenced symbol from MANGLED and append it to DECL.
+ Return the remaining string on success or NULL on failure. */
+static const char *
+dlang_symbol_backref (string *decl, const char *mangled,
+ struct dlang_info *info)
+{
+ /* An identifier back reference always points to a digit 0 to 9.
+
+ IdentifierBackRef:
+ Q NumberBackRef
+ ^
+ */
+ const char *backref;
+ unsigned long len;
+
+ /* Get position of the back reference. */
+ mangled = dlang_backref (mangled, &backref, info);
+
+ /* Must point to a simple identifier. */
+ backref = dlang_number (backref, &len);
+ if (backref == NULL)
+ return NULL;
+
+ backref = dlang_lname (decl, backref, len);
+ if (backref == NULL)
+ return NULL;
+
+ return mangled;
+}
+
+/* Demangle a back referenced type from MANGLED and append it to DECL.
+ IS_FUNCTION is 1 if the back referenced type is expected to be a function.
+ Return the remaining string on success or NULL on failure. */
+static const char *
+dlang_type_backref (string *decl, const char *mangled, struct dlang_info *info,
+ int is_function)
+{
+ /* A type back reference always points to a letter.
+
+ TypeBackRef:
+ Q NumberBackRef
+ ^
+ */
+ const char *backref;
+
+ /* If we appear to be moving backwards through the mangle string, then
+ bail as this may be a recursive back reference. */
+ if (mangled - info->s >= info->last_backref)
+ return NULL;
+
+ int save_refpos = info->last_backref;
+ info->last_backref = mangled - info->s;
+
+ /* Get position of the back reference. */
+ mangled = dlang_backref (mangled, &backref, info);
+
+ /* Must point to a type. */
+ if (is_function)
+ backref = dlang_function_type (decl, backref, info);
+ else
+ backref = dlang_type (decl, backref, info);
+
+ info->last_backref = save_refpos;
+
+ if (backref == NULL)
+ return NULL;
+
+ return mangled;
+}
+
+/* Extract the beginning of a symbol name from MANGLED and
+ return 1 on success or 0 on failure. */
+static int
+dlang_symbol_name_p (const char *mangled, struct dlang_info *info)
+{
+ long ret;
+ const char *qref = mangled;
-static const char *dlang_parse_tuple (string *, const char *);
+ if (ISDIGIT (*mangled))
+ return 1;
-static const char *dlang_parse_template (string *, const char *, long);
+ if (mangled[0] == '_' && mangled[1] == '_'
+ && (mangled[2] == 'T' || mangled[2] == 'U'))
+ return 1;
+ if (*mangled != 'Q')
+ return 0;
+
+ mangled = dlang_decode_backref (mangled + 1, &ret);
+ if (mangled == NULL || ret > qref - info->s)
+ return 0;
+
+ return ISDIGIT (qref[-ret]);
+}
/* Demangle the calling convention from MANGLED and append it to DECL.
Return the remaining string on success or NULL on failure. */
mangled++;
string_append (decl, "return ");
continue;
+ case 'l': /* scope */
+ mangled++;
+ string_append (decl, "scope ");
+ continue;
+ case 'm': /* @live */
+ mangled++;
+ string_append (decl, "@live ");
+ continue;
default: /* unknown attribute */
return NULL;
return mangled;
}
+/* Demangle the function type from MANGLED without the return type.
+ The arguments are appended to ARGS, the calling convention is appended
+ to CALL and attributes are appended to ATTR. Any of these can be NULL
+ to throw the information away. Return the remaining string on success
+ or NULL on failure. */
+static const char *
+dlang_function_type_noreturn (string *args, string *call, string *attr,
+ const char *mangled, struct dlang_info *info)
+{
+ string dump;
+ string_init (&dump);
+
+ /* Skip over calling convention and attributes. */
+ mangled = dlang_call_convention (call ? call : &dump, mangled);
+ mangled = dlang_attributes (attr ? attr : &dump, mangled);
+
+ if (args)
+ string_append (args, "(");
+
+ mangled = dlang_function_args (args ? args : &dump, mangled, info);
+ if (args)
+ string_append (args, ")");
+
+ string_delete (&dump);
+ return mangled;
+}
+
/* Demangle the function type from MANGLED and append it to DECL.
Return the remaining string on success or NULL on failure. */
static const char *
-dlang_function_type (string *decl, const char *mangled)
+dlang_function_type (string *decl, const char *mangled, struct dlang_info *info)
{
string attr, args, type;
- size_t szattr, szargs, sztype;
if (mangled == NULL || *mangled == '\0')
return NULL;
string_init (&args);
string_init (&type);
- /* Function call convention. */
- mangled = dlang_call_convention (decl, mangled);
-
- /* Function attributes. */
- mangled = dlang_attributes (&attr, mangled);
- szattr = string_length (&attr);
-
- /* Function arguments. */
- mangled = dlang_function_args (&args, mangled);
- szargs = string_length (&args);
+ mangled = dlang_function_type_noreturn (&args, decl, &attr, mangled, info);
/* Function return type. */
- mangled = dlang_type (&type, mangled);
- sztype = string_length (&type);
+ mangled = dlang_type (&type, mangled, info);
/* Append to decl in order. */
- string_appendn (decl, type.b, sztype);
- string_append (decl, "(");
- string_appendn (decl, args.b, szargs);
- string_append (decl, ") ");
- string_appendn (decl, attr.b, szattr);
+ string_appendn (decl, type.b, string_length (&type));
+ string_appendn (decl, args.b, string_length (&args));
+ string_append (decl, " ");
+ string_appendn (decl, attr.b, string_length (&attr));
string_delete (&attr);
string_delete (&args);
/* Demangle the argument list from MANGLED and append it to DECL.
Return the remaining string on success or NULL on failure. */
static const char *
-dlang_function_args (string *decl, const char *mangled)
+dlang_function_args (string *decl, const char *mangled, struct dlang_info *info)
{
size_t n = 0;
switch (*mangled)
{
+ case 'I': /* in(T) */
+ mangled++;
+ string_append (decl, "in ");
+ if (*mangled == 'K') /* in ref(T) */
+ {
+ mangled++;
+ string_append (decl, "ref ");
+ }
+ break;
case 'J': /* out(T) */
mangled++;
string_append (decl, "out ");
string_append (decl, "lazy ");
break;
}
- mangled = dlang_type (decl, mangled);
+ mangled = dlang_type (decl, mangled, info);
}
return mangled;
/* Demangle the type from MANGLED and append it to DECL.
Return the remaining string on success or NULL on failure. */
static const char *
-dlang_type (string *decl, const char *mangled)
+dlang_type (string *decl, const char *mangled, struct dlang_info *info)
{
if (mangled == NULL || *mangled == '\0')
return NULL;
case 'O': /* shared(T) */
mangled++;
string_append (decl, "shared(");
- mangled = dlang_type (decl, mangled);
+ mangled = dlang_type (decl, mangled, info);
string_append (decl, ")");
return mangled;
case 'x': /* const(T) */
mangled++;
string_append (decl, "const(");
- mangled = dlang_type (decl, mangled);
+ mangled = dlang_type (decl, mangled, info);
string_append (decl, ")");
return mangled;
case 'y': /* immutable(T) */
mangled++;
string_append (decl, "immutable(");
- mangled = dlang_type (decl, mangled);
+ mangled = dlang_type (decl, mangled, info);
string_append (decl, ")");
return mangled;
case 'N':
{
mangled++;
string_append (decl, "inout(");
- mangled = dlang_type (decl, mangled);
+ mangled = dlang_type (decl, mangled, info);
string_append (decl, ")");
return mangled;
}
{
mangled++;
string_append (decl, "__vector(");
- mangled = dlang_type (decl, mangled);
+ mangled = dlang_type (decl, mangled, info);
string_append (decl, ")");
return mangled;
}
return NULL;
case 'A': /* dynamic array (T[]) */
mangled++;
- mangled = dlang_type (decl, mangled);
+ mangled = dlang_type (decl, mangled, info);
string_append (decl, "[]");
return mangled;
case 'G': /* static array (T[N]) */
num++;
mangled++;
}
- mangled = dlang_type (decl, mangled);
+ mangled = dlang_type (decl, mangled, info);
string_append (decl, "[");
string_appendn (decl, numptr, num);
string_append (decl, "]");
mangled++;
string_init (&type);
- mangled = dlang_type (&type, mangled);
+ mangled = dlang_type (&type, mangled, info);
sztype = string_length (&type);
- mangled = dlang_type (decl, mangled);
+ mangled = dlang_type (decl, mangled, info);
string_append (decl, "[");
string_appendn (decl, type.b, sztype);
string_append (decl, "]");
}
case 'P': /* pointer (T*) */
mangled++;
- /* Function pointer types don't include the trailing asterisk. */
- switch (*mangled)
+ if (!dlang_call_convention_p (mangled))
{
- case 'F': case 'U': case 'W':
- case 'V': case 'R': case 'Y':
- mangled = dlang_function_type (decl, mangled);
- string_append (decl, "function");
+ mangled = dlang_type (decl, mangled, info);
+ string_append (decl, "*");
return mangled;
}
- mangled = dlang_type (decl, mangled);
- string_append (decl, "*");
+ /* Fall through */
+ case 'F': /* function T (D) */
+ case 'U': /* function T (C) */
+ case 'W': /* function T (Windows) */
+ case 'V': /* function T (Pascal) */
+ case 'R': /* function T (C++) */
+ case 'Y': /* function T (Objective-C) */
+ /* Function pointer types don't include the trailing asterisk. */
+ mangled = dlang_function_type (decl, mangled, info);
+ string_append (decl, "function");
return mangled;
- case 'I': /* ident T */
case 'C': /* class T */
case 'S': /* struct T */
case 'E': /* enum T */
case 'T': /* typedef T */
mangled++;
- return dlang_parse_symbol (decl, mangled, dlang_type_name);
+ return dlang_parse_qualified (decl, mangled, info, 0);
case 'D': /* delegate T */
{
string mods;
mangled = dlang_type_modifiers (&mods, mangled);
szmods = string_length (&mods);
- mangled = dlang_function_type (decl, mangled);
+ /* Back referenced function type. */
+ if (*mangled == 'Q')
+ mangled = dlang_type_backref (decl, mangled, info, 1);
+ else
+ mangled = dlang_function_type (decl, mangled, info);
+
string_append (decl, "delegate");
string_appendn (decl, mods.b, szmods);
}
case 'B': /* tuple T */
mangled++;
- return dlang_parse_tuple (decl, mangled);
+ return dlang_parse_tuple (decl, mangled, info);
/* Basic types */
case 'n':
}
return NULL;
+ /* Back referenced type. */
+ case 'Q':
+ return dlang_type_backref (decl, mangled, info, 0);
+
default: /* unhandled */
return NULL;
}
/* Extract the identifier from MANGLED and append it to DECL.
Return the remaining string on success or NULL on failure. */
static const char *
-dlang_identifier (string *decl, const char *mangled,
- enum dlang_symbol_kinds kind)
+dlang_identifier (string *decl, const char *mangled, struct dlang_info *info)
{
- char *endptr;
- long len;
+ unsigned long len;
if (mangled == NULL || *mangled == '\0')
return NULL;
- len = strtol (mangled, &endptr, 10);
+ if (*mangled == 'Q')
+ return dlang_symbol_backref (decl, mangled, info);
- if (endptr == NULL || len <= 0)
- return NULL;
+ /* May be a template instance without a length prefix. */
+ if (mangled[0] == '_' && mangled[1] == '_'
+ && (mangled[2] == 'T' || mangled[2] == 'U'))
+ return dlang_parse_template (decl, mangled, info, TEMPLATE_LENGTH_UNKNOWN);
- /* In template parameter symbols, the first character of the mangled
- name can be a digit. This causes ambiguity issues because the
- digits of the two numbers are adjacent. */
- if (kind == dlang_template_param)
- {
- long psize = len;
- char *pend;
- int saved = string_length (decl);
+ const char *endptr = dlang_number (mangled, &len);
- /* Work backwards until a match is found. */
- for (pend = endptr; endptr != NULL; pend--)
- {
- mangled = pend;
+ if (endptr == NULL || len == 0)
+ return NULL;
- /* Reached the beginning of the pointer to the name length,
- try parsing the entire symbol. */
- if (psize == 0)
- {
- psize = len;
- pend = endptr;
- endptr = NULL;
- }
+ if (strlen (endptr) < len)
+ return NULL;
- /* Check whether template parameter is a function with a valid
- return type or an untyped identifier. */
- if (ISDIGIT (*mangled))
- mangled = dlang_parse_symbol (decl, mangled, dlang_template_ident);
- else if (strncmp (mangled, "_D", 2) == 0)
- {
- mangled += 2;
- mangled = dlang_parse_symbol (decl, mangled, dlang_function);
- }
+ mangled = endptr;
- /* Check for name length mismatch. */
- if (mangled && (mangled - pend) == psize)
- return mangled;
+ /* May be a template instance with a length prefix. */
+ if (len >= 5 && mangled[0] == '_' && mangled[1] == '_'
+ && (mangled[2] == 'T' || mangled[2] == 'U'))
+ return dlang_parse_template (decl, mangled, info, len);
- psize /= 10;
- string_setlength (decl, saved);
- }
+ return dlang_lname (decl, mangled, len);
+}
- /* No match on any combinations. */
- return NULL;
- }
- else
+/* Extract the plain identifier from MANGLED and prepend/append it to DECL
+ with special treatment for some magic compiler generted symbols.
+ Return the remaining string on success or NULL on failure. */
+static const char *
+dlang_lname (string *decl, const char *mangled, unsigned long len)
+{
+ switch (len)
{
- if (strlen (endptr) < (size_t) len)
- return NULL;
-
- mangled = endptr;
-
- /* May be a template instance. */
- if (len >= 5 && strncmp (mangled, "__T", 3) == 0)
+ case 6:
+ if (strncmp (mangled, "__ctor", len) == 0)
{
- /* Template symbol. */
- if (ISDIGIT (mangled[3]) && mangled[3] != '0')
- return dlang_parse_template (decl, mangled, len);
-
- return NULL;
+ /* Constructor symbol for a class/struct. */
+ string_append (decl, "this");
+ mangled += len;
+ return mangled;
}
-
- switch (len)
+ else if (strncmp (mangled, "__dtor", len) == 0)
{
- case 6:
- if (strncmp (mangled, "__ctor", len) == 0)
- {
- /* Constructor symbol for a class/struct. */
- string_append (decl, "this");
- mangled += len;
- return mangled;
- }
- else if (strncmp (mangled, "__dtor", len) == 0)
- {
- /* Destructor symbol for a class/struct. */
- string_append (decl, "~this");
- mangled += len;
- return mangled;
- }
- else if (strncmp (mangled, "__initZ", len+1) == 0)
- {
- /* The static initialiser for a given symbol. */
- string_append (decl, "init$");
- mangled += len;
- return mangled;
- }
- else if (strncmp (mangled, "__vtblZ", len+1) == 0)
- {
- /* The vtable symbol for a given class. */
- string_prepend (decl, "vtable for ");
- string_setlength (decl, string_length (decl) - 1);
- mangled += len;
- return mangled;
- }
- break;
-
- case 7:
- if (strncmp (mangled, "__ClassZ", len+1) == 0)
- {
- /* The classinfo symbol for a given class. */
- string_prepend (decl, "ClassInfo for ");
- string_setlength (decl, string_length (decl) - 1);
- mangled += len;
- return mangled;
- }
- break;
+ /* Destructor symbol for a class/struct. */
+ string_append (decl, "~this");
+ mangled += len;
+ return mangled;
+ }
+ else if (strncmp (mangled, "__initZ", len + 1) == 0)
+ {
+ /* The static initialiser for a given symbol. */
+ string_prepend (decl, "initializer for ");
+ string_setlength (decl, string_length (decl) - 1);
+ mangled += len;
+ return mangled;
+ }
+ else if (strncmp (mangled, "__vtblZ", len + 1) == 0)
+ {
+ /* The vtable symbol for a given class. */
+ string_prepend (decl, "vtable for ");
+ string_setlength (decl, string_length (decl) - 1);
+ mangled += len;
+ return mangled;
+ }
+ break;
- case 10:
- if (strncmp (mangled, "__postblitMFZ", len+3) == 0)
- {
- /* Postblit symbol for a struct. */
- string_append (decl, "this(this)");
- mangled += len + 3;
- return mangled;
- }
- break;
+ case 7:
+ if (strncmp (mangled, "__ClassZ", len + 1) == 0)
+ {
+ /* The classinfo symbol for a given class. */
+ string_prepend (decl, "ClassInfo for ");
+ string_setlength (decl, string_length (decl) - 1);
+ mangled += len;
+ return mangled;
+ }
+ break;
- case 11:
- if (strncmp (mangled, "__InterfaceZ", len+1) == 0)
- {
- /* The interface symbol for a given class. */
- string_prepend (decl, "Interface for ");
- string_setlength (decl, string_length (decl) - 1);
- mangled += len;
- return mangled;
- }
- break;
+ case 10:
+ if (strncmp (mangled, "__postblitMFZ", len + 3) == 0)
+ {
+ /* Postblit symbol for a struct. */
+ string_append (decl, "this(this)");
+ mangled += len + 3;
+ return mangled;
+ }
+ break;
- case 12:
- if (strncmp (mangled, "__ModuleInfoZ", len+1) == 0)
- {
- /* The ModuleInfo symbol for a given module. */
- string_prepend (decl, "ModuleInfo for ");
- string_setlength (decl, string_length (decl) - 1);
- mangled += len;
- return mangled;
- }
- break;
+ case 11:
+ if (strncmp (mangled, "__InterfaceZ", len + 1) == 0)
+ {
+ /* The interface symbol for a given class. */
+ string_prepend (decl, "Interface for ");
+ string_setlength (decl, string_length (decl) - 1);
+ mangled += len;
+ return mangled;
}
+ break;
- string_appendn (decl, mangled, len);
- mangled += len;
+ case 12:
+ if (strncmp (mangled, "__ModuleInfoZ", len + 1) == 0)
+ {
+ /* The ModuleInfo symbol for a given module. */
+ string_prepend (decl, "ModuleInfo for ");
+ string_setlength (decl, string_length (decl) - 1);
+ mangled += len;
+ return mangled;
+ }
+ break;
}
+ string_appendn (decl, mangled, len);
+ mangled += len;
+
return mangled;
}
if (type == 'a' || type == 'u' || type == 'w')
{
/* Parse character value. */
- char value[10];
- int pos = 10;
+ char value[20];
+ int pos = sizeof(value);
int width = 0;
- char *endptr;
- long val = strtol (mangled, &endptr, 10);
+ unsigned long val;
- if (endptr == NULL || val < 0)
+ mangled = dlang_number (mangled, &val);
+ if (mangled == NULL)
return NULL;
string_append (decl, "'");
for (; width > 0; width--)
value[--pos] = '0';
- string_appendn (decl, &(value[pos]), 10 - pos);
+ string_appendn (decl, &(value[pos]), sizeof(value) - pos);
}
string_append (decl, "'");
- mangled = endptr;
}
else if (type == 'b')
{
/* Parse boolean value. */
- char *endptr;
- long val = strtol (mangled, &endptr, 10);
+ unsigned long val;
- if (endptr == NULL || val < 0)
+ mangled = dlang_number (mangled, &val);
+ if (mangled == NULL)
return NULL;
string_append (decl, val ? "true" : "false");
- mangled = endptr;
}
else
{
const char *numptr = mangled;
size_t num = 0;
+ if (! ISDIGIT (*mangled))
+ return NULL;
+
while (ISDIGIT (*mangled))
{
num++;
static const char *
dlang_parse_real (string *decl, const char *mangled)
{
- char buffer[64];
- int len = 0;
-
/* Handle NAN and +-INF. */
if (strncmp (mangled, "NAN", 3) == 0)
{
/* Hexadecimal prefix and leading bit. */
if (*mangled == 'N')
{
- buffer[len++] = '-';
+ string_append (decl, "-");
mangled++;
}
if (!ISXDIGIT (*mangled))
return NULL;
- buffer[len++] = '0';
- buffer[len++] = 'x';
- buffer[len++] = *mangled;
- buffer[len++] = '.';
+ string_append (decl, "0x");
+ string_appendn (decl, mangled, 1);
+ string_append (decl, ".");
mangled++;
/* Significand. */
while (ISXDIGIT (*mangled))
{
- buffer[len++] = *mangled;
+ string_appendn (decl, mangled, 1);
mangled++;
}
if (*mangled != 'P')
return NULL;
- buffer[len++] = 'p';
+ string_append (decl, "p");
mangled++;
if (*mangled == 'N')
{
- buffer[len++] = '-';
+ string_append (decl, "-");
mangled++;
}
while (ISDIGIT (*mangled))
{
- buffer[len++] = *mangled;
+ string_appendn (decl, mangled, 1);
mangled++;
}
- /* Write out the demangled hexadecimal, rather than trying to
- convert the buffer into a floating-point value. */
- buffer[len] = '\0';
- len = strlen (buffer);
- string_appendn (decl, buffer, len);
return mangled;
}
-/* Convert VAL from an ascii hexdigit to value. */
-static char
-ascii2hex (char val)
-{
- if (val >= 'a' && val <= 'f')
- return (val - 'a' + 10);
-
- if (val >= 'A' && val <= 'F')
- return (val - 'A' + 10);
-
- if (val >= '0' && val <= '9')
- return (val - '0');
-
- return 0;
-}
-
/* Extract the string value from MANGLED and append it to DECL.
Return the remaining string on success or NULL on failure. */
static const char *
dlang_parse_string (string *decl, const char *mangled)
{
char type = *mangled;
- char *endptr;
- long len;
+ unsigned long len;
mangled++;
- len = strtol (mangled, &endptr, 10);
-
- if (endptr == NULL || len < 0)
- return NULL;
-
- mangled = endptr;
- if (*mangled != '_')
+ mangled = dlang_number (mangled, &len);
+ if (mangled == NULL || *mangled != '_')
return NULL;
mangled++;
string_append (decl, "\"");
while (len--)
{
- if (ISXDIGIT (mangled[0]) && ISXDIGIT (mangled[1]))
+ char val;
+ const char *endptr = dlang_hexdigit (mangled, &val);
+
+ if (endptr == NULL)
+ return NULL;
+
+ /* Sanitize white and non-printable characters. */
+ switch (val)
{
- char a = ascii2hex (mangled[0]);
- char b = ascii2hex (mangled[1]);
- char val = (a << 4) | b;
+ case ' ':
+ string_append (decl, " ");
+ break;
+ case '\t':
+ string_append (decl, "\\t");
+ break;
+ case '\n':
+ string_append (decl, "\\n");
+ break;
+ case '\r':
+ string_append (decl, "\\r");
+ break;
+ case '\f':
+ string_append (decl, "\\f");
+ break;
+ case '\v':
+ string_append (decl, "\\v");
+ break;
- /* Sanitize white and non-printable characters. */
- switch (val)
+ default:
+ if (ISPRINT (val))
+ string_appendn (decl, &val, 1);
+ else
{
- case ' ':
- string_append (decl, " ");
- break;
- case '\t':
- string_append (decl, "\\t");
- break;
- case '\n':
- string_append (decl, "\\n");
- break;
- case '\r':
- string_append (decl, "\\r");
- break;
- case '\f':
- string_append (decl, "\\f");
- break;
- case '\v':
- string_append (decl, "\\v");
- break;
-
- default:
- if (ISPRINT (val))
- string_appendn (decl, &val, 1);
- else
- {
- string_append (decl, "\\x");
- string_appendn (decl, mangled, 2);
- }
+ string_append (decl, "\\x");
+ string_appendn (decl, mangled, 2);
}
}
- else
- return NULL;
- mangled += 2;
+ mangled = endptr;
}
string_append (decl, "\"");
static const char *
dlang_parse_arrayliteral (string *decl, const char *mangled)
{
- char *endptr;
- long elements = strtol (mangled, &endptr, 10);
+ unsigned long elements;
- if (endptr == NULL || elements < 0)
+ mangled = dlang_number (mangled, &elements);
+ if (mangled == NULL)
return NULL;
- mangled = endptr;
string_append (decl, "[");
while (elements--)
{
mangled = dlang_value (decl, mangled, NULL, '\0');
+ if (mangled == NULL)
+ return NULL;
+
if (elements != 0)
string_append (decl, ", ");
}
static const char *
dlang_parse_assocarray (string *decl, const char *mangled)
{
- char *endptr;
- long elements = strtol (mangled, &endptr, 10);
+ unsigned long elements;
- if (endptr == NULL || elements < 0)
+ mangled = dlang_number (mangled, &elements);
+ if (mangled == NULL)
return NULL;
- mangled = endptr;
string_append (decl, "[");
while (elements--)
{
mangled = dlang_value (decl, mangled, NULL, '\0');
+ if (mangled == NULL)
+ return NULL;
+
string_append (decl, ":");
mangled = dlang_value (decl, mangled, NULL, '\0');
+ if (mangled == NULL)
+ return NULL;
if (elements != 0)
string_append (decl, ", ");
static const char *
dlang_parse_structlit (string *decl, const char *mangled, const char *name)
{
- char *endptr;
- long args = strtol (mangled, &endptr, 10);
+ unsigned long args;
- if (endptr == NULL || args < 0)
+ mangled = dlang_number (mangled, &args);
+ if (mangled == NULL)
return NULL;
- mangled = endptr;
if (name != NULL)
string_append (decl, name);
while (args--)
{
mangled = dlang_value (decl, mangled, NULL, '\0');
+ if (mangled == NULL)
+ return NULL;
+
if (args != 0)
string_append (decl, ", ");
}
case 'i':
mangled++;
- if (*mangled < '0' || *mangled > '9')
- return NULL;
/* Fall through */
+
+ /* There really should always be an `i' before encoded numbers, but there
+ wasn't in early versions of D2, so this case range must remain for
+ backwards compatibility. */
case '0': case '1': case '2': case '3': case '4':
case '5': case '6': case '7': case '8': case '9':
mangled = dlang_parse_integer (decl, mangled, type);
return mangled;
}
-/* Extract the type modifiers from MANGLED and return the string
- length that it consumes in MANGLED on success or 0 on failure. */
-static int
-dlang_type_modifier_p (const char *mangled)
+/* Extract and demangle the symbol in MANGLED and append it to DECL.
+ Returns the remaining signature on success or NULL on failure. */
+static const char *
+dlang_parse_mangle (string *decl, const char *mangled, struct dlang_info *info)
{
- int i;
-
- switch (*mangled)
- {
- case 'x': case 'y':
- return 1;
+ /* A D mangled symbol is comprised of both scope and type information.
+
+ MangleName:
+ _D QualifiedName Type
+ _D QualifiedName Z
+ ^
+ The caller should have guaranteed that the start pointer is at the
+ above location.
+ Note that type is never a function type, but only the return type of
+ a function or the type of a variable.
+ */
+ mangled += 2;
- case 'O':
- mangled++;
- i = dlang_type_modifier_p (mangled);
- return i + 1;
+ mangled = dlang_parse_qualified (decl, mangled, info, 1);
- case 'N':
- mangled++;
- if (*mangled == 'g')
+ if (mangled != NULL)
+ {
+ /* Artificial symbols end with 'Z' and have no type. */
+ if (*mangled == 'Z')
+ mangled++;
+ else
{
- mangled++;
- i = dlang_type_modifier_p (mangled);
- return i + 2;
- }
- }
-
- return 0;
-}
+ /* Discard the declaration or return type. */
+ string type;
-/* Extract the function calling convention from MANGLED and
- return 1 on success or 0 on failure. */
-static int
-dlang_call_convention_p (const char *mangled)
-{
- /* Prefix for functions needing 'this' */
- if (*mangled == 'M')
- {
- mangled++;
- /* Also skip over any type modifiers. */
- mangled += dlang_type_modifier_p (mangled);
+ string_init (&type);
+ mangled = dlang_type (&type, mangled, info);
+ string_delete (&type);
+ }
}
- switch (*mangled)
- {
- case 'F': case 'U': case 'V':
- case 'W': case 'R': case 'Y':
- return 1;
-
- default:
- return 0;
- }
+ return mangled;
}
-/* Extract and demangle the symbol in MANGLED and append it to DECL.
+/* Extract and demangle the qualified symbol in MANGLED and append it to DECL.
+ SUFFIX_MODIFIERS is 1 if we are printing modifiers on this after the symbol.
Returns the remaining signature on success or NULL on failure. */
static const char *
-dlang_parse_symbol (string *decl, const char *mangled,
- enum dlang_symbol_kinds kind)
+dlang_parse_qualified (string *decl, const char *mangled,
+ struct dlang_info *info, int suffix_modifiers)
{
- int saved;
+ /* Qualified names are identifiers separated by their encoded length.
+ Nested functions also encode their argument types without specifying
+ what they return.
+
+ QualifiedName:
+ SymbolFunctionName
+ SymbolFunctionName QualifiedName
+ ^
+
+ SymbolFunctionName:
+ SymbolName
+ SymbolName TypeFunctionNoReturn
+ SymbolName M TypeFunctionNoReturn
+ SymbolName M TypeModifiers TypeFunctionNoReturn
+
+ The start pointer should be at the above location.
+ */
size_t n = 0;
do
{
if (n++)
string_append (decl, ".");
- mangled = dlang_identifier (decl, mangled, kind);
+ /* Skip over anonymous symbols. */
+ while (*mangled == '0')
+ mangled++;
+
+ mangled = dlang_identifier (decl, mangled, info);
- if (mangled && dlang_call_convention_p (mangled))
+ /* Consume the encoded arguments. However if this is not followed by the
+ next encoded length or mangle type, then this is not a continuation of
+ a qualified name, in which case we backtrack and return the current
+ unconsumed position of the mangled decl. */
+ if (mangled && (*mangled == 'M' || dlang_call_convention_p (mangled)))
{
string mods;
- const char *start = NULL;
- int checkpoint = 0;
+ const char *start = mangled;
+ int saved = string_length (decl);
- /* Skip over 'this' parameter. */
- if (*mangled == 'M')
- mangled++;
+ /* Save the type modifiers for appending at the end if needed. */
+ string_init (&mods);
- /* We have reached here because we expect an extern(Pascal) function.
- However this is so rare, that it is more likely a template value
- parameter. Since this can't be assumed, first attempt parsing
- the symbol as a function, and then back out on failure. */
- if (*mangled == 'V')
+ /* Skip over 'this' parameter and type modifiers. */
+ if (*mangled == 'M')
{
- start = mangled;
- checkpoint = string_length (decl);
+ mangled++;
+ mangled = dlang_type_modifiers (&mods, mangled);
+ string_setlength (decl, saved);
}
- /* Save the type modifiers for appending at the end. */
- string_init (&mods);
- mangled = dlang_type_modifiers (&mods, mangled);
-
- /* Skip over calling convention and attributes in qualified name. */
- saved = string_length (decl);
- mangled = dlang_call_convention (decl, mangled);
- mangled = dlang_attributes (decl, mangled);
- string_setlength (decl, saved);
+ mangled = dlang_function_type_noreturn (decl, NULL, NULL,
+ mangled, info);
+ if (suffix_modifiers)
+ string_appendn (decl, mods.b, string_length (&mods));
- string_append (decl, "(");
- mangled = dlang_function_args (decl, mangled);
- string_append (decl, ")");
-
- /* Add any const/immutable/shared modifier. */
- string_appendn (decl, mods.b, string_length (&mods));
- string_delete (&mods);
-
- if (mangled == NULL && checkpoint != 0)
+ if (mangled == NULL || *mangled == '\0')
{
+ /* Did not match the rule we were looking for. */
mangled = start;
- string_setlength (decl, checkpoint);
+ string_setlength (decl, saved);
}
- }
- }
- while (mangled && ISDIGIT (*mangled));
-
- /* Only top-level symbols or function template parameters have
- a type that needs checking. */
- if (kind == dlang_top_level || kind == dlang_function)
- {
- /* Artificial symbols end with 'Z' and have no type. */
- if (mangled && *mangled == 'Z')
- mangled++;
- else
- {
- saved = string_length (decl);
- mangled = dlang_type (decl, mangled);
- string_setlength (decl, saved);
- }
- /* Check that the entire symbol was successfully demangled. */
- if (kind == dlang_top_level)
- {
- if (mangled == NULL || *mangled != '\0')
- return NULL;
+ string_delete (&mods);
}
}
+ while (mangled && dlang_symbol_name_p (mangled, info));
return mangled;
}
/* Demangle the tuple from MANGLED and append it to DECL.
Return the remaining string on success or NULL on failure. */
static const char *
-dlang_parse_tuple (string *decl, const char *mangled)
+dlang_parse_tuple (string *decl, const char *mangled, struct dlang_info *info)
{
- char *endptr;
- long elements = strtol (mangled, &endptr, 10);
+ unsigned long elements;
- if (endptr == NULL || elements < 0)
+ mangled = dlang_number (mangled, &elements);
+ if (mangled == NULL)
return NULL;
- mangled = endptr;
string_append (decl, "Tuple!(");
while (elements--)
{
- mangled = dlang_type (decl, mangled);
+ mangled = dlang_type (decl, mangled, info);
+ if (mangled == NULL)
+ return NULL;
+
if (elements != 0)
string_append (decl, ", ");
}
return mangled;
}
+/* Demangle the template symbol parameter from MANGLED and append it to DECL.
+ Return the remaining string on success or NULL on failure. */
+static const char *
+dlang_template_symbol_param (string *decl, const char *mangled,
+ struct dlang_info *info)
+{
+ if (strncmp (mangled, "_D", 2) == 0
+ && dlang_symbol_name_p (mangled + 2, info))
+ return dlang_parse_mangle (decl, mangled, info);
+
+ if (*mangled == 'Q')
+ return dlang_parse_qualified (decl, mangled, info, 0);
+
+ unsigned long len;
+ const char *endptr = dlang_number (mangled, &len);
+
+ if (endptr == NULL || len == 0)
+ return NULL;
+
+ /* In template parameter symbols generated by the frontend up to 2.076,
+ the symbol length is encoded and the first character of the mangled
+ name can be a digit. This causes ambiguity issues because the digits
+ of the two numbers are adjacent. */
+ long psize = len;
+ const char *pend;
+ int saved = string_length (decl);
+
+ /* Work backwards until a match is found. */
+ for (pend = endptr; endptr != NULL; pend--)
+ {
+ mangled = pend;
+
+ /* Reached the beginning of the pointer to the name length,
+ try parsing the entire symbol. */
+ if (psize == 0)
+ {
+ psize = len;
+ pend = endptr;
+ endptr = NULL;
+ }
+
+ /* Check whether template parameter is a function with a valid
+ return type or an untyped identifier. */
+ if (dlang_symbol_name_p (mangled, info))
+ mangled = dlang_parse_qualified (decl, mangled, info, 0);
+ else if (strncmp (mangled, "_D", 2) == 0
+ && dlang_symbol_name_p (mangled + 2, info))
+ mangled = dlang_parse_mangle (decl, mangled, info);
+
+ /* Check for name length mismatch. */
+ if (mangled && (endptr == NULL || (mangled - pend) == psize))
+ return mangled;
+
+ psize /= 10;
+ string_setlength (decl, saved);
+ }
+
+ /* No match on any combinations. */
+ return NULL;
+}
+
/* Demangle the argument list from MANGLED and append it to DECL.
Return the remaining string on success or NULL on failure. */
static const char *
-dlang_template_args (string *decl, const char *mangled)
+dlang_template_args (string *decl, const char *mangled, struct dlang_info *info)
{
size_t n = 0;
{
case 'S': /* Symbol parameter. */
mangled++;
- mangled = dlang_parse_symbol (decl, mangled, dlang_template_param);
+ mangled = dlang_template_symbol_param (decl, mangled, info);
break;
case 'T': /* Type parameter. */
mangled++;
- mangled = dlang_type (decl, mangled);
+ mangled = dlang_type (decl, mangled, info);
break;
case 'V': /* Value parameter. */
{
mangled++;
type = *mangled;
+ if (type == 'Q')
+ {
+ /* Value type is a back reference, peek at the real type. */
+ const char *backref;
+ if (dlang_backref (mangled, &backref, info) == NULL)
+ return NULL;
+
+ type = *backref;
+ }
+
/* In the few instances where the type is actually desired in
the output, it should precede the value from dlang_value. */
string_init (&name);
- mangled = dlang_type (&name, mangled);
+ mangled = dlang_type (&name, mangled, info);
string_need (&name, 1);
*(name.p) = '\0';
string_delete (&name);
break;
}
+ case 'X': /* Externally mangled parameter. */
+ {
+ unsigned long len;
+ const char *endptr;
+
+ mangled++;
+ endptr = dlang_number (mangled, &len);
+ if (endptr == NULL || strlen (endptr) < len)
+ return NULL;
+ string_appendn (decl, endptr, len);
+ mangled = endptr + len;
+ break;
+ }
default:
return NULL;
}
}
/* Extract and demangle the template symbol in MANGLED, expected to
- be made up of LEN characters, and append it to DECL.
+ be made up of LEN characters (-1 if unknown), and append it to DECL.
Returns the remaining signature on success or NULL on failure. */
static const char *
-dlang_parse_template (string *decl, const char *mangled, long len)
+dlang_parse_template (string *decl, const char *mangled,
+ struct dlang_info *info, unsigned long len)
{
const char *start = mangled;
+ string args;
/* Template instance names have the types and values of its parameters
encoded into it.
TemplateInstanceName:
Number __T LName TemplateArgs Z
+ Number __U LName TemplateArgs Z
^
The start pointer should be at the above location, and LEN should be
the value of the decoded number.
*/
- if (strncmp (mangled, "__T", 3) != 0)
+
+ /* Template symbol. */
+ if (!dlang_symbol_name_p (mangled + 3, info) || mangled[3] == '0')
return NULL;
mangled += 3;
/* Template identifier. */
- mangled = dlang_identifier (decl, mangled, dlang_template_ident);
+ mangled = dlang_identifier (decl, mangled, info);
/* Template arguments. */
+ string_init (&args);
+ mangled = dlang_template_args (&args, mangled, info);
+
string_append (decl, "!(");
- mangled = dlang_template_args (decl, mangled);
+ string_appendn (decl, args.b, string_length (&args));
string_append (decl, ")");
+ string_delete (&args);
+
/* Check for template name length mismatch. */
- if (mangled && (mangled - start) != len)
+ if (len != TEMPLATE_LENGTH_UNKNOWN
+ && mangled
+ && (unsigned long) (mangled - start) != len)
return NULL;
return mangled;
}
+/* Initialize the information structure we use to pass around information. */
+static void
+dlang_demangle_init_info (const char *mangled, int last_backref,
+ struct dlang_info *info)
+{
+ info->s = mangled;
+ info->last_backref = last_backref;
+}
+
/* Extract and demangle the symbol in MANGLED. Returns the demangled
signature on success or NULL on failure. */
}
else
{
- mangled += 2;
+ struct dlang_info info;
+
+ dlang_demangle_init_info (mangled, strlen (mangled), &info);
+ mangled = dlang_parse_mangle (&decl, mangled, &info);
- if (dlang_parse_symbol (&decl, mangled, dlang_top_level) == NULL)
+ /* Check that the entire symbol was successfully demangled. */
+ if (mangled == NULL || *mangled != '\0')
string_delete (&decl);
}
projects / thirdparty / binutils-gdb.git / blobdiff