mirror of
https://github.com/JakeHillion/drgn.git
synced 2024-12-23 17:53:07 +00:00
75c3679147
The current mixed Python/C implementation works well, but it has a couple of important limitations: - It's too slow for some common use cases, like iterating over large data structures. - It can't be reused in utilities written in other languages. This replaces the internals with a new library written in C, libdrgn. It includes Python bindings with mostly the same public interface as before, with some important improvements: - Types are now represented by a single Type class rather than the messy polymorphism in the Python implementation. - Qualifiers are a bitmask instead of a set of strings. - Bit fields are not considered a separate type. - The lvalue/rvalue terminology is replaced with reference/value. - Structure, union, and array values are better supported. - Function objects are supported. - Program distinguishes between lookups of variables, constants, and functions. The C rewrite is about 6x as fast as the original Python when using the Python bindings, and about 8x when using the C API directly. Currently, the exposed API in C is fairly conservative. In the future, the memory reader, type index, and object index APIs will probably be exposed for more flexibility.
132 lines
3.1 KiB
C
132 lines
3.1 KiB
C
// Copyright 2018-2019 - Omar Sandoval
|
|
// SPDX-License-Identifier: GPL-3.0+
|
|
|
|
/**
|
|
* @file
|
|
*
|
|
* Lexer interface.
|
|
*
|
|
* See @ref Lexer.
|
|
*/
|
|
|
|
#ifndef DRGN_LEXER_H
|
|
#define DRGN_LEXER_H
|
|
|
|
#include <stddef.h>
|
|
|
|
/**
|
|
* @ingroup Internals
|
|
*
|
|
* @defgroup Lexer Lexer
|
|
*
|
|
* Lexical analysis.
|
|
*
|
|
* This is a convenient interface for lexical analysis. @ref drgn_lexer provides
|
|
* the abstraction of a stack of tokens (@ref drgn_token) on top of a raw @ref
|
|
* drgn_lexer_func.
|
|
*
|
|
* @{
|
|
*/
|
|
|
|
struct drgn_error;
|
|
struct drgn_lexer;
|
|
struct drgn_token;
|
|
|
|
/**
|
|
* Lexer function.
|
|
*
|
|
* A lexer function does the work of lexing the next token in a string. It
|
|
* should initialize the passed in token and advance @ref drgn_lexer::p.
|
|
*/
|
|
typedef struct drgn_error *(*drgn_lexer_func)(struct drgn_lexer *,
|
|
struct drgn_token *);
|
|
|
|
/** Lexical token. */
|
|
struct drgn_token {
|
|
/** Kind of token as defined by the lexer function. */
|
|
int kind;
|
|
/**
|
|
* String value of the token (i.e., the lexeme).
|
|
*
|
|
* This points to the contents of the original string, so it isn't
|
|
* null-terminated.
|
|
*/
|
|
const char *value;
|
|
/** Length of the token value. */
|
|
size_t len;
|
|
};
|
|
|
|
/**
|
|
* Lexer instance.
|
|
*
|
|
* A lexer comprises a lexer function, a position, and a stack of tokens. Tokens
|
|
* can be pushed and popped onto the stack. When the stack is empty, a pop calls
|
|
* the lexer function instead.
|
|
*/
|
|
struct drgn_lexer {
|
|
/** Lexer function. */
|
|
drgn_lexer_func func;
|
|
/** Current position in the string. */
|
|
const char *p;
|
|
/** Stack of tokens. */
|
|
struct drgn_token *stack;
|
|
/** Number of tokens on the stack. */
|
|
size_t stack_len;
|
|
/** Allocated size of the stack. */
|
|
size_t stack_capacity;
|
|
};
|
|
|
|
/**
|
|
* Initialize a @ref drgn_lexer from a lexer function and a string.
|
|
*
|
|
* @param[in] lexer Lexer to initialize.
|
|
* @param[in] func Lexer function.
|
|
* @param[in] str String to lex.
|
|
*/
|
|
void drgn_lexer_init(struct drgn_lexer *lexer, drgn_lexer_func func,
|
|
const char *str);
|
|
|
|
/**
|
|
* Free memory allocated by a @ref drgn_lexer.
|
|
*
|
|
* @param[in] lexer Lexer to deinitialize.
|
|
*/
|
|
void drgn_lexer_deinit(struct drgn_lexer *lexer);
|
|
|
|
/**
|
|
* Return the next token from a @ref drgn_lexer.
|
|
*
|
|
* If there are tokens on the stack, this pops and returns the top token.
|
|
* Otherwise, this calls the lexer function to get the next token.
|
|
*
|
|
* @return @c NULL on success, non-@c NULL on error.
|
|
*/
|
|
struct drgn_error *drgn_lexer_pop(struct drgn_lexer *lexer,
|
|
struct drgn_token *token);
|
|
|
|
/**
|
|
* Push a token onto the stack of a @ref drgn_lexer.
|
|
*
|
|
* This token must have been returned by @ref drgn_lexer_pop().
|
|
*
|
|
* @return @c NULL on success, non-@c NULL on error.
|
|
*/
|
|
struct drgn_error *drgn_lexer_push(struct drgn_lexer *lexer,
|
|
const struct drgn_token *token);
|
|
|
|
/**
|
|
* Return the next token from a @ref drgn_lexer and leave it on top of the
|
|
* stack.
|
|
*
|
|
* This is equivalent to a call to @ref drgn_lexer_pop() immediately followed by
|
|
* a call to @ref drgn_lexer_push().
|
|
*
|
|
* @return @c NULL on success, non-@c NULL on error.
|
|
*/
|
|
struct drgn_error *drgn_lexer_peek(struct drgn_lexer *lexer,
|
|
struct drgn_token *token);
|
|
|
|
/** @} */
|
|
|
|
#endif /* DRGN_LEXER_H */
|