mirror of
https://github.com/EnterpriseDB/repmgr.git
synced 2026-03-22 22:56:29 +00:00
Convert configuration file parsing to use flex
Previously, repmgr was using a very simple ad-hoc string-based parser,
which had various limitations and allowed configuration files to be
created in a way which could cause confusion and/or unexpected
behaviour.
For example, it accepted strings enclosed in single quotes, but treated
strings enclosed in double quotes literally. A node_name defined thusly:
node_name="somenode"
would result in the literal value '"somenode"' being used, which could
lead to unobvious errors along the lines of:
no record found for ""somenode""
The configuration file parser has been adapted from the one used by
PostgreSQL itself, so behaves more-or-less identically (though some
functions such as file inclusion are not supported in repmgr).
This makes configuration parsing more robust and consistent;
additionally, error reporting will be more precise.
Note this does mean that some repmgr.conf items previously accepted
as valid by repmgr will now be rejected; in particular this includes
strings containing spaces which are not enclosed in single quotes.
This commit is contained in:
Ian Barwick
344
configfile-scan.l
Normal file
344
configfile-scan.l
Normal file
@@ -0,0 +1,344 @@
|
||||
/*
|
||||
* Scanner for the configuration file
|
||||
*/
|
||||
|
||||
%{
|
||||
|
||||
#include <setjmp.h>
|
||||
|
||||
#include "repmgr.h"
|
||||
#include "configfile.h"
|
||||
|
||||
/*
|
||||
* flex emits a yy_fatal_error() function that it calls in response to
|
||||
* critical errors like malloc failure, file I/O errors, and detection of
|
||||
* internal inconsistency. That function prints a message and calls exit().
|
||||
* Mutate it to instead call our handler, which jumps out of the parser.
|
||||
*/
|
||||
#undef fprintf
|
||||
#define fprintf(file, fmt, msg) CONF_flex_fatal(msg)
|
||||
|
||||
enum
|
||||
{
|
||||
CONF_ID = 1,
|
||||
CONF_STRING = 2,
|
||||
CONF_INTEGER = 3,
|
||||
CONF_REAL = 4,
|
||||
CONF_EQUALS = 5,
|
||||
CONF_UNQUOTED_STRING = 6,
|
||||
CONF_QUALIFIED_ID = 7,
|
||||
CONF_EOL = 99,
|
||||
CONF_ERROR = 100
|
||||
};
|
||||
|
||||
static unsigned int ConfigFileLineno;
|
||||
static const char *CONF_flex_fatal_errmsg;
|
||||
static sigjmp_buf *CONF_flex_fatal_jmp;
|
||||
|
||||
static char *CONF_scanstr(const char *s);
|
||||
static int CONF_flex_fatal(const char *msg);
|
||||
|
||||
%}
|
||||
|
||||
%option 8bit
|
||||
%option never-interactive
|
||||
%option nodefault
|
||||
%option noinput
|
||||
%option nounput
|
||||
%option noyywrap
|
||||
%option warn
|
||||
%option prefix="CONF_yy"
|
||||
|
||||
|
||||
SIGN ("-"|"+")
|
||||
DIGIT [0-9]
|
||||
HEXDIGIT [0-9a-fA-F]
|
||||
|
||||
UNIT_LETTER [a-zA-Z]
|
||||
|
||||
INTEGER {SIGN}?({DIGIT}+|0x{HEXDIGIT}+){UNIT_LETTER}*
|
||||
|
||||
EXPONENT [Ee]{SIGN}?{DIGIT}+
|
||||
REAL {SIGN}?{DIGIT}*"."{DIGIT}*{EXPONENT}?
|
||||
|
||||
LETTER [A-Za-z_\200-\377]
|
||||
LETTER_OR_DIGIT [A-Za-z_0-9\200-\377]
|
||||
|
||||
ID {LETTER}{LETTER_OR_DIGIT}*
|
||||
QUALIFIED_ID {ID}"."{ID}
|
||||
|
||||
UNQUOTED_STRING {LETTER}({LETTER_OR_DIGIT}|[-._:/])*
|
||||
STRING \'([^'\\\n]|\\.|\'\')*\'
|
||||
|
||||
%%
|
||||
|
||||
\n ConfigFileLineno++; return CONF_EOL;
|
||||
[ \t\r]+ /* eat whitespace */
|
||||
#.* /* eat comment (.* matches anything until newline) */
|
||||
|
||||
{ID} return CONF_ID;
|
||||
{QUALIFIED_ID} return CONF_QUALIFIED_ID;
|
||||
{STRING} return CONF_STRING;
|
||||
{UNQUOTED_STRING} return CONF_UNQUOTED_STRING;
|
||||
{INTEGER} return CONF_INTEGER;
|
||||
{REAL} return CONF_REAL;
|
||||
= return CONF_EQUALS;
|
||||
|
||||
. return CONF_ERROR;
|
||||
|
||||
%%
|
||||
|
||||
|
||||
extern bool
|
||||
ProcessConfigFile(FILE *fp, const char *config_file, t_configuration_options *options, ItemList *error_list, ItemList *warning_list)
|
||||
{
|
||||
volatile bool OK = true;
|
||||
volatile YY_BUFFER_STATE lex_buffer = NULL;
|
||||
sigjmp_buf flex_fatal_jmp;
|
||||
int errorcount;
|
||||
int token;
|
||||
|
||||
if (sigsetjmp(flex_fatal_jmp, 1) == 0)
|
||||
{
|
||||
CONF_flex_fatal_jmp = &flex_fatal_jmp;
|
||||
}
|
||||
else
|
||||
{
|
||||
/*
|
||||
* Regain control after a fatal, internal flex error. It may have
|
||||
* corrupted parser state. Consequently, abandon the file, but trust
|
||||
* that the state remains sane enough for yy_delete_buffer().
|
||||
*/
|
||||
item_list_append_format(error_list,
|
||||
"%s at file \"%s\" line %u",
|
||||
CONF_flex_fatal_errmsg, config_file, ConfigFileLineno);
|
||||
OK = false;
|
||||
goto cleanup;
|
||||
}
|
||||
|
||||
/*
|
||||
* Parse
|
||||
*/
|
||||
ConfigFileLineno = 1;
|
||||
errorcount = 0;
|
||||
|
||||
lex_buffer = yy_create_buffer(fp, YY_BUF_SIZE);
|
||||
yy_switch_to_buffer(lex_buffer);
|
||||
|
||||
/* This loop iterates once per logical line */
|
||||
while ((token = yylex()))
|
||||
{
|
||||
char *opt_name = NULL;
|
||||
char *opt_value = NULL;
|
||||
|
||||
if (token == CONF_EOL) /* empty or comment line */
|
||||
continue;
|
||||
|
||||
/* first token on line is option name */
|
||||
if (token != CONF_ID && token != CONF_QUALIFIED_ID)
|
||||
goto parse_error;
|
||||
opt_name = pstrdup(yytext);
|
||||
|
||||
/* next we have an optional equal sign; discard if present */
|
||||
token = yylex();
|
||||
if (token == CONF_EQUALS)
|
||||
token = yylex();
|
||||
|
||||
/* now we must have the option value */
|
||||
if (token != CONF_ID &&
|
||||
token != CONF_STRING &&
|
||||
token != CONF_INTEGER &&
|
||||
token != CONF_REAL &&
|
||||
token != CONF_UNQUOTED_STRING)
|
||||
goto parse_error;
|
||||
if (token == CONF_STRING) /* strip quotes and escapes */
|
||||
opt_value = CONF_scanstr(yytext);
|
||||
else
|
||||
opt_value = pstrdup(yytext);
|
||||
|
||||
/* now we'd like an end of line, or possibly EOF */
|
||||
token = yylex();
|
||||
if (token != CONF_EOL)
|
||||
{
|
||||
if (token != 0)
|
||||
goto parse_error;
|
||||
/* treat EOF like \n for line numbering purposes, cf bug 4752 */
|
||||
ConfigFileLineno++;
|
||||
}
|
||||
|
||||
/* OK, process the option name and value */
|
||||
|
||||
parse_configuration_item(options,
|
||||
error_list,
|
||||
warning_list,
|
||||
opt_name,
|
||||
opt_value);
|
||||
|
||||
/* break out of loop if read EOF, else loop for next line */
|
||||
if (token == 0)
|
||||
break;
|
||||
continue;
|
||||
|
||||
parse_error:
|
||||
/* release storage if we allocated any on this line */
|
||||
if (opt_name)
|
||||
pfree(opt_name);
|
||||
if (opt_value)
|
||||
pfree(opt_value);
|
||||
|
||||
/* report the error */
|
||||
if (token == CONF_EOL || token == 0)
|
||||
{
|
||||
item_list_append_format(error_list,
|
||||
_("syntax error in file \"%s\" line %u, near end of line"),
|
||||
config_file, ConfigFileLineno - 1);
|
||||
}
|
||||
else
|
||||
{
|
||||
item_list_append_format(error_list,
|
||||
_("syntax error in file \"%s\" line %u, near token \"%s\""),
|
||||
config_file, ConfigFileLineno, yytext);
|
||||
}
|
||||
OK = false;
|
||||
errorcount++;
|
||||
|
||||
/*
|
||||
* To avoid producing too much noise when fed a totally bogus file,
|
||||
* give up after 100 syntax errors per file (an arbitrary number).
|
||||
* Also, if we're only logging the errors at DEBUG level anyway, might
|
||||
* as well give up immediately. (This prevents postmaster children
|
||||
* from bloating the logs with duplicate complaints.)
|
||||
*/
|
||||
if (errorcount >= 100)
|
||||
{
|
||||
fprintf(stderr,
|
||||
_("too many syntax errors found, abandoning file \"%s\"\n"),
|
||||
config_file);
|
||||
break;
|
||||
}
|
||||
|
||||
/* resync to next end-of-line or EOF */
|
||||
while (token != CONF_EOL && token != 0)
|
||||
token = yylex();
|
||||
/* break out of loop on EOF */
|
||||
if (token == 0)
|
||||
break;
|
||||
}
|
||||
|
||||
cleanup:
|
||||
yy_delete_buffer(lex_buffer);
|
||||
|
||||
return OK;
|
||||
}
|
||||
|
||||
|
||||
/*
|
||||
* scanstr
|
||||
*
|
||||
* Strip the quotes surrounding the given string, and collapse any embedded
|
||||
* '' sequences and backslash escapes.
|
||||
*
|
||||
* the string returned is palloc'd and should eventually be pfree'd by the
|
||||
* caller.
|
||||
*/
|
||||
static char *
|
||||
CONF_scanstr(const char *s)
|
||||
{
|
||||
char *newStr;
|
||||
int len,
|
||||
i,
|
||||
j;
|
||||
|
||||
Assert(s != NULL && s[0] == '\'');
|
||||
len = strlen(s);
|
||||
Assert(s != NULL);
|
||||
|
||||
Assert(len >= 2);
|
||||
Assert(s[len - 1] == '\'');
|
||||
|
||||
/* Skip the leading quote; we'll handle the trailing quote below */
|
||||
s++, len--;
|
||||
|
||||
/* Since len still includes trailing quote, this is enough space */
|
||||
newStr = palloc(len);
|
||||
|
||||
for (i = 0, j = 0; i < len; i++)
|
||||
{
|
||||
if (s[i] == '\\')
|
||||
{
|
||||
i++;
|
||||
switch (s[i])
|
||||
{
|
||||
case 'b':
|
||||
newStr[j] = '\b';
|
||||
break;
|
||||
case 'f':
|
||||
newStr[j] = '\f';
|
||||
break;
|
||||
case 'n':
|
||||
newStr[j] = '\n';
|
||||
break;
|
||||
case 'r':
|
||||
newStr[j] = '\r';
|
||||
break;
|
||||
case 't':
|
||||
newStr[j] = '\t';
|
||||
break;
|
||||
case '0':
|
||||
case '1':
|
||||
case '2':
|
||||
case '3':
|
||||
case '4':
|
||||
case '5':
|
||||
case '6':
|
||||
case '7':
|
||||
{
|
||||
int k;
|
||||
long octVal = 0;
|
||||
|
||||
for (k = 0;
|
||||
s[i + k] >= '0' && s[i + k] <= '7' && k < 3;
|
||||
k++)
|
||||
octVal = (octVal << 3) + (s[i + k] - '0');
|
||||
i += k - 1;
|
||||
newStr[j] = ((char) octVal);
|
||||
}
|
||||
break;
|
||||
default:
|
||||
newStr[j] = s[i];
|
||||
break;
|
||||
} /* switch */
|
||||
}
|
||||
else if (s[i] == '\'' && s[i + 1] == '\'')
|
||||
{
|
||||
/* doubled quote becomes just one quote */
|
||||
newStr[j] = s[++i];
|
||||
}
|
||||
else
|
||||
newStr[j] = s[i];
|
||||
j++;
|
||||
}
|
||||
|
||||
/* We copied the ending quote to newStr, so replace with \0 */
|
||||
Assert(j > 0 && j <= len);
|
||||
newStr[--j] = '\0';
|
||||
|
||||
return newStr;
|
||||
}
|
||||
|
||||
|
||||
/*
|
||||
* Flex fatal errors bring us here. Stash the error message and jump back to
|
||||
* ParseConfigFp(). Assume all msg arguments point to string constants; this
|
||||
* holds for flex 2.5.31 (earliest we support) and flex 2.5.35 (latest as of
|
||||
* this writing). Otherwise, we would need to copy the message.
|
||||
*
|
||||
* We return "int" since this takes the place of calls to fprintf().
|
||||
*/
|
||||
static int
|
||||
CONF_flex_fatal(const char *msg)
|
||||
{
|
||||
CONF_flex_fatal_errmsg = msg;
|
||||
siglongjmp(*CONF_flex_fatal_jmp, 1);
|
||||
return 0; /* keep compiler quiet */
|
||||
}
|
||||
Reference in New Issue
Block a user