php-src/Zend/zend_language_scanner.h
Alex Dowad 80598f1250 Syntax errors caused by unclosed {, [, ( mention specific location
Aside from a few very specific syntax errors for which detailed exceptions are
thrown, generally PHP just emits the default error messages generated by bison on syntax
error. These messages are very uninformative; they just say "Unexpected ... at line ...".

This is most problematic with constructs which can span an arbitrary number of lines, such
as blocks of code delimited by { }, 'if' conditions delimited by ( ), and so on. If a closing
delimiter is missed, the block will run for the entire remainder of the source file (which
could be thousands of lines), and then at the end, a parse error will be thrown with the
dreaded words: "Unexpected end of file".

Therefore, track the positions of opening and closing delimiters and ensure that they match
up correctly. If any mismatch or missing delimiter is detected, immediately throw a parse
error which points the user to the offending line. This is best done in the *lexer* and not
in the parser.

Thanks to Nikita Popov and George Peter Banyard for suggesting improvements.

Fixes bug #79368.
Closes GH-5364.
2020-04-14 11:22:23 +02:00

84 lines
2.9 KiB
C

/*
+----------------------------------------------------------------------+
| Zend Engine |
+----------------------------------------------------------------------+
| Copyright (c) Zend Technologies Ltd. (http://www.zend.com) |
+----------------------------------------------------------------------+
| This source file is subject to version 2.00 of the Zend license, |
| that is bundled with this package in the file LICENSE, and is |
| available through the world-wide-web at the following url: |
| http://www.zend.com/license/2_00.txt. |
| If you did not receive a copy of the Zend license and are unable to |
| obtain it through the world-wide-web, please send a note to |
| license@zend.com so we can mail you a copy immediately. |
+----------------------------------------------------------------------+
| Authors: Andi Gutmans <andi@php.net> |
| Zeev Suraski <zeev@php.net> |
+----------------------------------------------------------------------+
*/
#ifndef ZEND_SCANNER_H
#define ZEND_SCANNER_H
typedef struct _zend_lex_state {
unsigned int yy_leng;
unsigned char *yy_start;
unsigned char *yy_text;
unsigned char *yy_cursor;
unsigned char *yy_marker;
unsigned char *yy_limit;
int yy_state;
zend_stack state_stack;
zend_ptr_stack heredoc_label_stack;
zend_stack nest_location_stack; /* for syntax error reporting */
zend_file_handle *in;
uint32_t lineno;
zend_string *filename;
/* original (unfiltered) script */
unsigned char *script_org;
size_t script_org_size;
/* filtered script */
unsigned char *script_filtered;
size_t script_filtered_size;
/* input/output filters */
zend_encoding_filter input_filter;
zend_encoding_filter output_filter;
const zend_encoding *script_encoding;
/* hooks */
void (*on_event)(zend_php_scanner_event event, int token, int line, void *context);
void *on_event_context;
zend_ast *ast;
zend_arena *ast_arena;
} zend_lex_state;
typedef struct _zend_heredoc_label {
char *label;
int length;
int indentation;
zend_bool indentation_uses_spaces;
} zend_heredoc_label;
/* Track locations of unclosed {, [, (, etc. for better syntax error reporting */
typedef struct _zend_nest_location {
char text;
int lineno;
} zend_nest_location;
BEGIN_EXTERN_C()
ZEND_API void zend_save_lexical_state(zend_lex_state *lex_state);
ZEND_API void zend_restore_lexical_state(zend_lex_state *lex_state);
ZEND_API int zend_prepare_string_for_scanning(zval *str, const char *filename);
ZEND_API void zend_multibyte_yyinput_again(zend_encoding_filter old_input_filter, const zend_encoding *old_encoding);
ZEND_API int zend_multibyte_set_filter(const zend_encoding *onetime_encoding);
ZEND_API void zend_lex_tstring(zval *zv);
END_EXTERN_C()
#endif