zzy/scc
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat(lexer, preprocessor): replace cstring conversion with copy and refactor macro expansion

Browse Source 
- Replace `scc_cstring_from_cstr(scc_cstring_as_cstr(...))` with `scc_cstring_copy()` in lexer to fix memory leaks
- Extract macro expansion logic into separate `expand_macro.c` file
- Remove `expand_stack` parameter from `scc_pp_expand_macro()` function
- Add new parsing functions for macro replacement lists and arguments
- Add string utility functions for whitespace trimming and string joining
- Update memory stream documentation for clarity
This commit is contained in:
zzy
2025-12-15 20:24:39 +08:00
parent 73d74f5e13
commit 07f5d9331b
15 changed files with 574 additions and 346 deletions
Download Patch File Download Diff File Expand all files Collapse all files

16
runtime/libcore/include/core_str.h
View File

@@ -20,6 +20,7 @@ typedef struct scc_cstring {
*
* @return cstring_t 初始化后的对象
*/
// FIXME need using `init` beacuse it not malloc
static inline scc_cstring_t scc_cstring_new(void) {
return (scc_cstring_t){.data = null, .size = 0, .cap = 0};
}
@@ -48,6 +49,10 @@ static inline scc_cstring_t scc_cstring_from_cstr(const char *s) {
return (scc_cstring_t){.size = len + 1, .cap = len + 1, .data = data};
}
static inline scc_cstring_t scc_cstring_copy(const scc_cstring_t *s) {
return scc_cstring_from_cstr(s->data);
}
/**
* @brief 释放动态字符串占用的内存资源
*
@@ -182,4 +187,15 @@ static inline char *scc_cstring_as_cstr(const scc_cstring_t *str) {
return str->data;
}
static inline char *scc_cstring_move_cstr(scc_cstring_t *str) {
if (str == null || str->data == null) {
return "";
}
char *ret = str->data;
str->data = null;
str->cap = 0;
str->size = 0;
return ret;
}
#endif /* __SCC_CORE_STR_H__ */

10
runtime/libcore/include/core_stream.h
View File

@@ -100,7 +100,7 @@ typedef struct scc_mem_probe_stream {
usize data_length;
usize curr_pos; // 当前读取位置
usize probe_pos; // 探针位置（用于peek）
cbool owned; // 是否拥有数据（需要释放）
cbool owned; // 是否拥有数据（如果拥有将会自动释放）
} scc_mem_probe_stream_t;
/**
@@ -109,22 +109,22 @@ typedef struct scc_mem_probe_stream {
* @param stream 流结构指针
* @param data 数据指针
* @param length 数据长度
* @param need_copy 是否需要复制数据
* @param owned 是否拥有数据（如果拥有将会自动释放）
* @return core_probe_stream_t* 成功返回流指针，失败返回NULL
*/
scc_probe_stream_t *scc_mem_probe_stream_init(scc_mem_probe_stream_t *stream,
const char *data, usize length,
cbool need_copy);
cbool owned);
/**
* @brief 构造内存探针流(其中drop会自动释放内存)
*
* @param data
* @param length
* @param need_copy
* @param owned 是否拥有数据（如果拥有将会自动释放）
* @return scc_probe_stream_t*
*/
scc_probe_stream_t *scc_mem_probe_stream_new(const char *data, usize length,
cbool need_copy);
cbool owned);
#endif
#endif /* __SMCC_CORE_PROBE_STREAM_H__ */

23
runtime/libcore/src/stream.c
View File

@@ -125,7 +125,7 @@ static void mem_probe_stream_drop(scc_probe_stream_t *_stream) {
scc_probe_stream_t *scc_mem_probe_stream_init(scc_mem_probe_stream_t *stream,
const char *data, usize length,
cbool need_copy) {
cbool owned) {
if (stream == null || data == null) {
LOG_ERROR("param error");
return null;
@@ -133,22 +133,11 @@ scc_probe_stream_t *scc_mem_probe_stream_init(scc_mem_probe_stream_t *stream,
if (length == 0) {
LOG_WARN("input memory is empty");
need_copy = false;
owned = false;
}
stream->owned = need_copy;
if (need_copy) {
char *buf = (char *)scc_malloc(length);
if (buf == null) {
LOG_ERROR("malloc error");
return null;
}
scc_memcpy(buf, data, length);
stream->data = buf;
} else {
stream->data = data;
}
stream->owned = owned;
stream->data = data;
stream->data_length = length;
stream->curr_pos = 0;
stream->probe_pos = 0;
@@ -176,7 +165,7 @@ static void scc_owned_mem_stream_drop(scc_probe_stream_t *_stream) {
}
scc_probe_stream_t *scc_mem_probe_stream_new(const char *data, usize length,
cbool need_copy) {
cbool owned) {
scc_mem_probe_stream_t *stream =
(scc_mem_probe_stream_t *)scc_malloc(sizeof(scc_mem_probe_stream_t));
if (stream == null) {
@@ -184,7 +173,7 @@ scc_probe_stream_t *scc_mem_probe_stream_new(const char *data, usize length,
}
scc_probe_stream_t *ret =
scc_mem_probe_stream_init(stream, data, length, need_copy);
scc_mem_probe_stream_init(stream, data, length, owned);
stream->stream.drop = scc_owned_mem_stream_drop;
Assert(ret != null);
return ret;

8
runtime/libutils/include/hashmap.h → runtime/libutils/include/hashtable.h
View File

@@ -1,12 +1,12 @@
/**
* @file hashmap.h
* @file hashtable.h
* @brief 开放寻址法哈希表实现
*
* 提供基于向量容器的哈希表实现，支持动态扩容和墓碑机制
*/
#ifndef __SCC_HASHMAP_H__
#define __SCC_HASHMAP_H__
#ifndef __SCC_HASHTABLE_H__
#define __SCC_HASHTABLE_H__
#include <libcore.h>
@@ -121,4 +121,4 @@ typedef int (*scc_hashtable_iter_fn)(const void *key, void *value,
void scc_hashtable_foreach(scc_hashtable_t *ht, scc_hashtable_iter_fn iter_func,
void *context);
#endif /* __SCC_HASHMAP_H__ */
#endif /* __SCC_HASHTABLE_H__ */

4
runtime/libutils/include/libutils.h
View File

@@ -1,9 +1,9 @@
#ifndef __SMCC_UTILS_H__
#define __SMCC_UTILS_H__
#include "hashmap.h"
#include "hashtable.h"
#include "kllist.h"
#include "strpool.h"
#include <libcore.h>
#endif // __SMCC_UTILS_H__
#endif /* __SMCC_UTILS_H__ */

2
runtime/libutils/include/strpool.h
View File

@@ -8,7 +8,7 @@
#ifndef __SCC_STRPOOL_H__
#define __SCC_STRPOOL_H__
#include "hashmap.h"
#include "hashtable.h"
#include <libcore.h>
/**

2
runtime/libutils/src/hashmap.c → runtime/libutils/src/hashtable.c
View File

@@ -1,4 +1,4 @@
#include <hashmap.h>
#include <hashtable.h>
#ifndef SCC_INIT_HASHMAP_SIZE
#define SCC_INIT_HASHMAP_SIZE (32)

112
runtime/libutils/src/vector-gdb.py
View File

@@ -1,112 +0,0 @@
# vector_gdb.py
import gdb # type: ignore
from gdb.printing import PrettyPrinter # type: ignore
class VectorPrinter:
"""兼容新旧注册方式的最终方案"""
def __init__(self, val: gdb.Value):
self.val:gdb.Value = val
def check_type(self) -> bool:
"""类型检查（兼容匿名结构体）"""
try:
if self.val.type.code != gdb.TYPE_CODE_STRUCT:
return False
fields = self.val.type.fields()
if not fields:
return False
exp = ['size', 'cap', 'data']
for t in fields:
if t.name in exp:
exp.remove(t.name)
else:
return False
return True
except gdb.error:
return False
def to_string(self):
if not self.check_type():
return "Not a vector"
return "vector({} size={}, cap={})".format(
self.val.address,
self.val['size'],
self.val['cap'],
)
def display_hint(self):
return 'array'
def children(self):
"""生成数组元素（关键改进点）"""
if not self.check_type():
return []
size = int(self.val['size'])
cap = int(self.val['cap'])
data_ptr = self.val['data']
if cap == 0 or data_ptr == 0:
return []
# 使用 GDB 内置数组转换
array = data_ptr.dereference()
array = array.cast(data_ptr.type.target().array(cap - 1))
for i in range(size):
# state = "<used>" if i < size else "<unused>"
try:
value = array[i]
yield (f"[{i}] {value.type} {value.address}", value)
except gdb.MemoryError:
yield (f"[{i}]", "<invalid>")
# 注册方式一：传统append方法（您之前有效的方式）self
def append_printer():
gdb.pretty_printers.append(
lambda val: VectorPrinter(val) if VectorPrinter(val).check_type() else None
)
# 注册方式二：新版注册方法（备用方案）
def register_new_printer():
class VectorPrinterLocator(PrettyPrinter):
def __init__(self):
super().__init__("vector_printer")
def __call__(self, val):
ret = VectorPrinter(val).check_type()
print(f"ret {ret}, type {val.type}, {[(i.name, i.type) for i in val.type.fields()]}")
return None
gdb.printing.register_pretty_printer(
gdb.current_objfile(),
VectorPrinterLocator()
)
# 双重注册保证兼容性
append_printer() # 保留您原来有效的方式
# register_new_printer() # 添加新版注册
class VectorInfoCommand(gdb.Command):
"""保持原有命令不变"""
def __init__(self):
super().__init__("vector_info", gdb.COMMAND_USER)
def invoke(self, argument, from_tty):
val = gdb.parse_and_eval(argument)
printer = VectorPrinter(val)
if not printer.check_type():
print("Invalid vector")
return
print("=== Vector Details ===")
print("Size:", val['size'])
print("Capacity:", val['cap'])
print("Elements:")
for name, value in printer.children():
print(f" {name}: {value}")
VectorInfoCommand()

222
runtime/runtime_gdb.py Normal file
View File

@@ -0,0 +1,222 @@
"https://sourceware.org/gdb/current/onlinedocs/gdb.html/Python-API.html#Python-API"
import gdb # type: ignore
class VectorPrinter(gdb.ValuePrinter):
"""兼容新旧注册方式的最终方案"""
def __init__(self, val: gdb.Value):
self.val: gdb.Value = val
@staticmethod
def check_type(val: gdb.Value) -> bool:
"""类型检查（兼容匿名结构体）"""
try:
if val.type.code not in (gdb.TYPE_CODE_STRUCT, gdb.TYPE_CODE_TYPEDEF):
return False
if val.type.name == "scc_cstring_t":
return False
fields = val.type.fields()
if not fields:
return False
exp = ["size", "cap", "data"]
for t in fields:
if t.name in exp:
exp.remove(t.name)
else:
return False
return True
except gdb.error:
return False
except ValueError:
return False
except TypeError:
return False
except Exception as e:
print(f"[DEBUG] Unknown exception type: {type(e).__name__}")
print(f"[DEBUG] Exception details: {e}")
print(
f"[DEBUG] val type: {val.type if hasattr(val, 'type') else 'no type attr'}"
)
return False
def to_string(self):
"""
GDB will call this method to display the string representation
of the value passed to the object's constructor.
This is a basic method, and is optional.
When printing from the CLI, if the to_string method exists,
then GDB will prepend its result to the values returned by children.
Exactly how this formatting is done is dependent on the display hint,
and may change as more hints are added. Also, depending on the print settings
(see Print Settings), the CLI may print just the result of to_string
in a stack trace, omitting the result of children.
If this method returns a string, it is printed verbatim.
Otherwise, if this method returns an instance of gdb.Value,
then GDB prints this value. This may result in a call to another pretty-printer.
If instead the method returns a Python value which is convertible to a gdb.Value,
then GDB performs the conversion and prints the resulting value. Again,
this may result in a call to another pretty-printer. Python scalars
(integers, floats, and booleans) and strings are convertible to gdb.Value;
other types are not.
Finally, if this method returns None then no further operations are performed
in this method and nothing is printed.
If the result is not one of these types, an exception is raised.
https://sourceware.org/gdb/current/onlinedocs/gdb.html/Pretty-Printing-API.html#Pretty-Printing-API
"""
return (
f"vector({self.val.address} size={self.val['size']}, cap={self.val['cap']})"
)
def display_hint(self):
"""
The CLI may call this method and use its result to change the formatting of a value.
The result will also be supplied to an MI consumer as a 'displayhint'
attribute of the variable being printed.
This is a basic method, and is optional. If it does exist,
this method must return a string or the special value None.
Some display hints are predefined by GDB:
'array'
Indicate that the object being printed is “array-like”.
The CLI uses this to respect parameters such as set print elements and set print array.
'map'
Indicate that the object being printed is “map-like”,
and that the children of this value can be assumed to alternate between keys and values.
'string'
Indicate that the object being printed is “string-like”.
If the printer's to_string method returns a Python string of some kind,
then GDB will call its internal language-specific string-printing function
to format the string. For the CLI this means adding quotation marks, possibly
escaping some characters, respecting set print elements, and the like.
The special value None causes GDB to apply the default display rules.
https://sourceware.org/gdb/current/onlinedocs/gdb.html/Pretty-Printing-API.html#Pretty-Printing-API
"""
return "array"
def num_children(self):
"""
This is not a basic method, so GDB will only ever call it for objects
derived from gdb.ValuePrinter.
If available, this method should return the number of children.
None may be returned if the number can't readily be computed.
https://sourceware.org/gdb/current/onlinedocs/gdb.html/Pretty-Printing-API.html#Pretty-Printing-API
"""
return int(self.val["size"])
def children(self):
"""
This is not a basic method, so GDB will only ever call it for objects
derived from gdb.ValuePrinter.
If available, this method should return the child item (that is,
a tuple holding the name and value of this child) indicated by n.
Indices start at zero.
GDB provides a function which can be used to look up the default
pretty-printer for a gdb.Value:
https://sourceware.org/gdb/current/onlinedocs/gdb.html/Pretty-Printing-API.html#Pretty-Printing-API
"""
size = int(self.val["size"])
cap = int(self.val["cap"])
data_ptr = self.val["data"]
if cap == 0 or data_ptr == 0:
return []
# 使用 GDB 内置数组转换
array = data_ptr.dereference()
array = array.cast(data_ptr.type.target().array(cap - 1))
for i in range(size):
# state = "<used>" if i < size else "<unused>"
try:
value = array[i]
yield (f"[{i}] {value.type} {value.address}", value)
except gdb.MemoryError:
yield (f"[{i}]", "<invalid>")
class HashTablePrinter(gdb.ValuePrinter):
def __init__(self, val: gdb.Value):
self.val: gdb.Value = val
@staticmethod
def check_type(val: gdb.Value) -> bool:
if val.type.name in ["scc_hashtable_t", "scc_hashtable"]:
return True
return False
def append_printer():
"注册方式一：传统append方法（您之前有效的方式）self"
gdb.pretty_printers.append(
lambda val: VectorPrinter(val) if VectorPrinter.check_type(val) else None
)
def register_new_printer():
"注册方式二：新版注册方法（备用方案）"
def str_lookup_function(val):
if VectorPrinter.check_type(val) is False:
return None
ret = VectorPrinter(val)
# print(
# f"ret {ret}, type {val.type.name}, {[(i.name, i.type) for i in val.type.fields()]}"
# )
return ret
gdb.printing.register_pretty_printer(gdb.current_objfile(), str_lookup_function)
# if gdb.current_progspace() is not None:
# pts = gdb.current_progspace().pretty_printers
# print(pts, len(pts))
# pts.append(str_lookup_function)
class VectorInfoCommand(gdb.Command):
"""保持原有命令不变"""
def __init__(self):
super().__init__("vector_info", gdb.COMMAND_USER)
def invoke(self, argument, from_tty):
val = gdb.parse_and_eval(argument)
if not VectorPrinter.check_type(val):
print("Invalid vector")
return
printer = VectorPrinter(val)
print("=== Vector Details ===")
print("Size:", val["size"])
print("Capacity:", val["cap"])
print("Elements:")
for name, value in printer.children():
print(f" {name}: {value}")
if __name__ == "__main__":
# 双重注册保证兼容性
# append_printer() # 保留您原来有效的方式
register_new_printer() # 添加新版注册
VectorInfoCommand()