mirror of
https://github.com/php/php-src.git
synced 2025-08-16 22:18:50 +02:00
3b0f051193
Albeit CSV is still a widespread data exchange format, it has never been officially standardized. There exists, however, the “informational” RFC 4180[1] which has no notion of escape characters, but rather defines `escaped` as strings enclosed in double-quotes where contained double-quotes have to be doubled. While this concept is supported by PHP's implementation (`$enclosure`), the `$escape` sometimes interferes, so that `fgetcsv()` is unable to correctly parse externally generated CSV, and `fputcsv()` is sometimes generating non-compliant CSV. Since PHP's `$escape` concept is availble for many years, we cannot drop it for BC reasons (even though many consider it as bug). Instead we allow to pass an empty string as `$escape` parameter to the respective functions, which results in ignoring/omitting any escaping, and as such is more inline with RFC 4180. It is noteworthy that this is almost no userland BC break, since formerly most functions did not accept an empty string, and failed in this case. The only exception was `str_getcsv()` which did accept an empty string, and used a backslash as escape character then (which appears to be unintended behavior, anyway). The changed functions are `fputcsv()`, `fgetcsv()` and `str_getcsv()`, and also the `::setCsvControl()`, `::getCsvControl()`, `::fputcsv()`, and `::fgetcsv()` methods of `SplFileObject`. The implementation also changes the type of the escape parameter of the PHP_APIs `php_fgetcsv()` and `php_fputcsv()` from `char` to `int`, where `PHP_CSV_NO_ESCAPE` means to ignore/omit escaping. The parameter accepts the same values as `isalpha()` and friends, i.e. “the value of which shall be representable as an `unsigned char` or shall equal the value of the macro `EOF`. If the argument has any other value, the behavior is undefined.” This is a subtle BC break, since the character `chr(128)` has the value `-1` if `char` is signed, and so likely would be confused with `EOF` when converted to `int`. We consider this BC break to be acceptable, since it's rather unlikely that anybody uses `chr(128)` as escape character, and it easily can be fixed by casting all `escape` arguments to `unsigned char`. This patch implements the feature requests 38301[2] and 51496[3]. [1] <https://tools.ietf.org/html/rfc4180> [2] <https://bugs.php.net/bug.php?id=38301> [3] <https://bugs.php.net/bug.php?id=51496>
146 lines
4.6 KiB
C
146 lines
4.6 KiB
C
/*
|
|
+----------------------------------------------------------------------+
|
|
| PHP Version 7 |
|
|
+----------------------------------------------------------------------+
|
|
| Copyright (c) 1997-2018 The PHP Group |
|
|
+----------------------------------------------------------------------+
|
|
| This source file is subject to version 3.01 of the PHP 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.php.net/license/3_01.txt |
|
|
| If you did not receive a copy of the PHP license and are unable to |
|
|
| obtain it through the world-wide-web, please send a note to |
|
|
| license@php.net so we can mail you a copy immediately. |
|
|
+----------------------------------------------------------------------+
|
|
| Author: Rasmus Lerdorf <rasmus@lerdorf.on.ca> |
|
|
+----------------------------------------------------------------------+
|
|
*/
|
|
|
|
#ifndef FILE_H
|
|
#define FILE_H
|
|
|
|
#include "php_network.h"
|
|
|
|
PHP_MINIT_FUNCTION(file);
|
|
PHP_MSHUTDOWN_FUNCTION(file);
|
|
|
|
PHP_FUNCTION(tempnam);
|
|
PHP_NAMED_FUNCTION(php_if_tmpfile);
|
|
PHP_NAMED_FUNCTION(php_if_fopen);
|
|
PHPAPI PHP_FUNCTION(fclose);
|
|
PHP_FUNCTION(popen);
|
|
PHP_FUNCTION(pclose);
|
|
PHPAPI PHP_FUNCTION(feof);
|
|
PHPAPI PHP_FUNCTION(fread);
|
|
PHPAPI PHP_FUNCTION(fgetc);
|
|
PHPAPI PHP_FUNCTION(fgets);
|
|
PHP_FUNCTION(fscanf);
|
|
PHPAPI PHP_FUNCTION(fgetss);
|
|
PHP_FUNCTION(fgetcsv);
|
|
PHP_FUNCTION(fputcsv);
|
|
PHPAPI PHP_FUNCTION(fwrite);
|
|
PHPAPI PHP_FUNCTION(fflush);
|
|
PHPAPI PHP_FUNCTION(rewind);
|
|
PHPAPI PHP_FUNCTION(ftell);
|
|
PHPAPI PHP_FUNCTION(fseek);
|
|
PHP_FUNCTION(mkdir);
|
|
PHP_FUNCTION(rmdir);
|
|
PHPAPI PHP_FUNCTION(fpassthru);
|
|
PHP_FUNCTION(readfile);
|
|
PHP_FUNCTION(umask);
|
|
PHP_FUNCTION(rename);
|
|
PHP_FUNCTION(unlink);
|
|
PHP_FUNCTION(copy);
|
|
PHP_FUNCTION(file);
|
|
PHP_FUNCTION(file_get_contents);
|
|
PHP_FUNCTION(file_put_contents);
|
|
PHP_FUNCTION(get_meta_tags);
|
|
PHP_FUNCTION(flock);
|
|
PHP_FUNCTION(fd_set);
|
|
PHP_FUNCTION(fd_isset);
|
|
#if HAVE_REALPATH || defined(ZTS)
|
|
PHP_FUNCTION(realpath);
|
|
#endif
|
|
#ifdef HAVE_FNMATCH
|
|
PHP_FUNCTION(fnmatch);
|
|
#endif
|
|
PHP_NAMED_FUNCTION(php_if_ftruncate);
|
|
PHP_NAMED_FUNCTION(php_if_fstat);
|
|
PHP_FUNCTION(sys_get_temp_dir);
|
|
|
|
PHP_MINIT_FUNCTION(user_streams);
|
|
|
|
PHPAPI int php_le_stream_context(void);
|
|
PHPAPI int php_set_sock_blocking(php_socket_t socketd, int block);
|
|
PHPAPI int php_copy_file(const char *src, const char *dest);
|
|
PHPAPI int php_copy_file_ex(const char *src, const char *dest, int src_chk);
|
|
PHPAPI int php_copy_file_ctx(const char *src, const char *dest, int src_chk, php_stream_context *ctx);
|
|
PHPAPI int php_mkdir_ex(const char *dir, zend_long mode, int options);
|
|
PHPAPI int php_mkdir(const char *dir, zend_long mode);
|
|
|
|
#define PHP_CSV_NO_ESCAPE EOF
|
|
PHPAPI void php_fgetcsv(php_stream *stream, char delimiter, char enclosure, int escape_char, size_t buf_len, char *buf, zval *return_value);
|
|
PHPAPI size_t php_fputcsv(php_stream *stream, zval *fields, char delimiter, char enclosure, int escape_char);
|
|
|
|
#define META_DEF_BUFSIZE 8192
|
|
|
|
#define PHP_FILE_USE_INCLUDE_PATH 1
|
|
#define PHP_FILE_IGNORE_NEW_LINES 2
|
|
#define PHP_FILE_SKIP_EMPTY_LINES 4
|
|
#define PHP_FILE_APPEND 8
|
|
#define PHP_FILE_NO_DEFAULT_CONTEXT 16
|
|
|
|
typedef enum _php_meta_tags_token {
|
|
TOK_EOF = 0,
|
|
TOK_OPENTAG,
|
|
TOK_CLOSETAG,
|
|
TOK_SLASH,
|
|
TOK_EQUAL,
|
|
TOK_SPACE,
|
|
TOK_ID,
|
|
TOK_STRING,
|
|
TOK_OTHER
|
|
} php_meta_tags_token;
|
|
|
|
typedef struct _php_meta_tags_data {
|
|
php_stream *stream;
|
|
int ulc;
|
|
int lc;
|
|
char *input_buffer;
|
|
char *token_data;
|
|
int token_len;
|
|
int in_meta;
|
|
} php_meta_tags_data;
|
|
|
|
php_meta_tags_token php_next_meta_token(php_meta_tags_data *);
|
|
|
|
typedef struct {
|
|
int pclose_ret;
|
|
size_t def_chunk_size;
|
|
zend_long auto_detect_line_endings;
|
|
zend_long default_socket_timeout;
|
|
char *user_agent; /* for the http wrapper */
|
|
char *from_address; /* for the ftp and http wrappers */
|
|
const char *user_stream_current_filename; /* for simple recursion protection */
|
|
php_stream_context *default_context;
|
|
HashTable *stream_wrappers; /* per-request copy of url_stream_wrappers_hash */
|
|
HashTable *stream_filters; /* per-request copy of stream_filters_hash */
|
|
HashTable *wrapper_errors; /* key: wrapper address; value: linked list of char* */
|
|
int pclose_wait;
|
|
#if defined(HAVE_GETHOSTBYNAME_R)
|
|
struct hostent tmp_host_info;
|
|
char *tmp_host_buf;
|
|
size_t tmp_host_buf_len;
|
|
#endif
|
|
} php_file_globals;
|
|
|
|
#ifdef ZTS
|
|
#define FG(v) ZEND_TSRMG(file_globals_id, php_file_globals *, v)
|
|
extern PHPAPI int file_globals_id;
|
|
#else
|
|
#define FG(v) (file_globals.v)
|
|
extern PHPAPI php_file_globals file_globals;
|
|
#endif
|
|
|
|
|
|
#endif /* FILE_H */
|