add first bits of a (custom) config parser
This commit is contained in:
Michael Stapelberg
446
src/config_parser.c
Normal file
446
src/config_parser.c
Normal file
@ -0,0 +1,446 @@
|
||||
#undef I3__FILE__
|
||||
#define I3__FILE__ "config_parser.c"
|
||||
/*
|
||||
* vim:ts=4:sw=4:expandtab
|
||||
*
|
||||
* i3 - an improved dynamic tiling window manager
|
||||
* © 2009-2012 Michael Stapelberg and contributors (see also: LICENSE)
|
||||
*
|
||||
* config_parser.c: hand-written parser to parse configuration directives.
|
||||
*
|
||||
* See also src/commands_parser.c for rationale on why we use a custom parser.
|
||||
*
|
||||
*/
|
||||
#include <stdio.h>
|
||||
#include <stdlib.h>
|
||||
#include <string.h>
|
||||
#include <unistd.h>
|
||||
#include <stdbool.h>
|
||||
#include <stdint.h>
|
||||
|
||||
#include "all.h"
|
||||
|
||||
// Macros to make the YAJL API a bit easier to use.
|
||||
#define y(x, ...) yajl_gen_ ## x (command_output.json_gen, ##__VA_ARGS__)
|
||||
#define ystr(str) yajl_gen_string(command_output.json_gen, (unsigned char*)str, strlen(str))
|
||||
|
||||
/*******************************************************************************
|
||||
* The data structures used for parsing. Essentially the current state and a
|
||||
* list of tokens for that state.
|
||||
*
|
||||
* The GENERATED_* files are generated by generate-commands-parser.pl with the
|
||||
* input parser-specs/configs.spec.
|
||||
******************************************************************************/
|
||||
|
||||
#include "GENERATED_config_enums.h"
|
||||
|
||||
typedef struct token {
|
||||
char *name;
|
||||
char *identifier;
|
||||
/* This might be __CALL */
|
||||
cmdp_state next_state;
|
||||
union {
|
||||
uint16_t call_identifier;
|
||||
} extra;
|
||||
} cmdp_token;
|
||||
|
||||
typedef struct tokenptr {
|
||||
cmdp_token *array;
|
||||
int n;
|
||||
} cmdp_token_ptr;
|
||||
|
||||
#include "GENERATED_config_tokens.h"
|
||||
|
||||
/*******************************************************************************
|
||||
* The (small) stack where identified literals are stored during the parsing
|
||||
* of a single command (like $workspace).
|
||||
******************************************************************************/
|
||||
|
||||
struct stack_entry {
|
||||
/* Just a pointer, not dynamically allocated. */
|
||||
const char *identifier;
|
||||
char *str;
|
||||
};
|
||||
|
||||
/* 10 entries should be enough for everybody. */
|
||||
static struct stack_entry stack[10];
|
||||
|
||||
/*
|
||||
* Pushes a string (identified by 'identifier') on the stack. We simply use a
|
||||
* single array, since the number of entries we have to store is very small.
|
||||
*
|
||||
*/
|
||||
static void push_string(const char *identifier, char *str) {
|
||||
for (int c = 0; c < 10; c++) {
|
||||
if (stack[c].identifier != NULL &&
|
||||
strcmp(stack[c].identifier, identifier) != 0)
|
||||
continue;
|
||||
if (stack[c].identifier == NULL) {
|
||||
/* Found a free slot, let’s store it here. */
|
||||
stack[c].identifier = identifier;
|
||||
stack[c].str = str;
|
||||
} else {
|
||||
/* Append the value. */
|
||||
sasprintf(&(stack[c].str), "%s,%s", stack[c].str, str);
|
||||
}
|
||||
return;
|
||||
}
|
||||
|
||||
/* When we arrive here, the stack is full. This should not happen and
|
||||
* means there’s either a bug in this parser or the specification
|
||||
* contains a command with more than 10 identified tokens. */
|
||||
fprintf(stderr, "BUG: commands_parser stack full. This means either a bug "
|
||||
"in the code, or a new command which contains more than "
|
||||
"10 identified tokens.\n");
|
||||
exit(1);
|
||||
}
|
||||
|
||||
// XXX: ideally, this would be const char. need to check if that works with all
|
||||
// called functions.
|
||||
static char *get_string(const char *identifier) {
|
||||
for (int c = 0; c < 10; c++) {
|
||||
if (stack[c].identifier == NULL)
|
||||
break;
|
||||
if (strcmp(identifier, stack[c].identifier) == 0)
|
||||
return stack[c].str;
|
||||
}
|
||||
return NULL;
|
||||
}
|
||||
|
||||
static void clear_stack(void) {
|
||||
for (int c = 0; c < 10; c++) {
|
||||
if (stack[c].str != NULL)
|
||||
free(stack[c].str);
|
||||
stack[c].identifier = NULL;
|
||||
stack[c].str = NULL;
|
||||
}
|
||||
}
|
||||
|
||||
// TODO: remove this if it turns out we don’t need it for testing.
|
||||
#if 0
|
||||
/*******************************************************************************
|
||||
* A dynamically growing linked list which holds the criteria for the current
|
||||
* command.
|
||||
******************************************************************************/
|
||||
|
||||
typedef struct criterion {
|
||||
char *type;
|
||||
char *value;
|
||||
|
||||
TAILQ_ENTRY(criterion) criteria;
|
||||
} criterion;
|
||||
|
||||
static TAILQ_HEAD(criteria_head, criterion) criteria =
|
||||
TAILQ_HEAD_INITIALIZER(criteria);
|
||||
|
||||
/*
|
||||
* Stores the given type/value in the list of criteria.
|
||||
* Accepts a pointer as first argument, since it is 'call'ed by the parser.
|
||||
*
|
||||
*/
|
||||
static void push_criterion(void *unused_criteria, const char *type,
|
||||
const char *value) {
|
||||
struct criterion *criterion = malloc(sizeof(struct criterion));
|
||||
criterion->type = strdup(type);
|
||||
criterion->value = strdup(value);
|
||||
TAILQ_INSERT_TAIL(&criteria, criterion, criteria);
|
||||
}
|
||||
|
||||
/*
|
||||
* Clears the criteria linked list.
|
||||
* Accepts a pointer as first argument, since it is 'call'ed by the parser.
|
||||
*
|
||||
*/
|
||||
static void clear_criteria(void *unused_criteria) {
|
||||
struct criterion *criterion;
|
||||
while (!TAILQ_EMPTY(&criteria)) {
|
||||
criterion = TAILQ_FIRST(&criteria);
|
||||
free(criterion->type);
|
||||
free(criterion->value);
|
||||
TAILQ_REMOVE(&criteria, criterion, criteria);
|
||||
free(criterion);
|
||||
}
|
||||
}
|
||||
#endif
|
||||
|
||||
/*******************************************************************************
|
||||
* The parser itself.
|
||||
******************************************************************************/
|
||||
|
||||
static cmdp_state state;
|
||||
#ifndef TEST_PARSER
|
||||
static Match current_match;
|
||||
#endif
|
||||
static struct CommandResult subcommand_output;
|
||||
static struct CommandResult command_output;
|
||||
|
||||
#include "GENERATED_config_call.h"
|
||||
|
||||
|
||||
static void next_state(const cmdp_token *token) {
|
||||
//printf("token = name %s identifier %s\n", token->name, token->identifier);
|
||||
//printf("next_state = %d\n", token->next_state);
|
||||
if (token->next_state == __CALL) {
|
||||
subcommand_output.json_gen = command_output.json_gen;
|
||||
subcommand_output.needs_tree_render = false;
|
||||
GENERATED_call(token->extra.call_identifier, &subcommand_output);
|
||||
/* If any subcommand requires a tree_render(), we need to make the
|
||||
* whole parser result request a tree_render(). */
|
||||
if (subcommand_output.needs_tree_render)
|
||||
command_output.needs_tree_render = true;
|
||||
clear_stack();
|
||||
return;
|
||||
}
|
||||
|
||||
state = token->next_state;
|
||||
if (state == INITIAL) {
|
||||
clear_stack();
|
||||
}
|
||||
}
|
||||
|
||||
struct CommandResult *parse_config(const char *input) {
|
||||
DLOG("COMMAND: *%s*\n", input);
|
||||
state = INITIAL;
|
||||
|
||||
/* A YAJL JSON generator used for formatting replies. */
|
||||
#if YAJL_MAJOR >= 2
|
||||
command_output.json_gen = yajl_gen_alloc(NULL);
|
||||
#else
|
||||
command_output.json_gen = yajl_gen_alloc(NULL, NULL);
|
||||
#endif
|
||||
|
||||
y(array_open);
|
||||
command_output.needs_tree_render = false;
|
||||
|
||||
const char *walk = input;
|
||||
const size_t len = strlen(input);
|
||||
int c;
|
||||
const cmdp_token *token;
|
||||
bool token_handled;
|
||||
|
||||
// TODO: make this testable
|
||||
#ifndef TEST_PARSER
|
||||
cmd_criteria_init(¤t_match, &subcommand_output);
|
||||
#endif
|
||||
|
||||
/* The "<=" operator is intentional: We also handle the terminating 0-byte
|
||||
* explicitly by looking for an 'end' token. */
|
||||
while ((walk - input) <= len) {
|
||||
/* skip whitespace and newlines before every token */
|
||||
while ((*walk == ' ' || *walk == '\t' ||
|
||||
*walk == '\r' || *walk == '\n') && *walk != '\0')
|
||||
walk++;
|
||||
|
||||
//printf("remaining input: %s\n", walk);
|
||||
|
||||
cmdp_token_ptr *ptr = &(tokens[state]);
|
||||
token_handled = false;
|
||||
for (c = 0; c < ptr->n; c++) {
|
||||
token = &(ptr->array[c]);
|
||||
|
||||
/* A literal. */
|
||||
if (token->name[0] == '\'') {
|
||||
if (strncasecmp(walk, token->name + 1, strlen(token->name) - 1) == 0) {
|
||||
if (token->identifier != NULL)
|
||||
push_string(token->identifier, sstrdup(token->name + 1));
|
||||
walk += strlen(token->name) - 1;
|
||||
next_state(token);
|
||||
token_handled = true;
|
||||
break;
|
||||
}
|
||||
continue;
|
||||
}
|
||||
|
||||
if (strcmp(token->name, "string") == 0 ||
|
||||
strcmp(token->name, "word") == 0) {
|
||||
const char *beginning = walk;
|
||||
/* Handle quoted strings (or words). */
|
||||
if (*walk == '"') {
|
||||
beginning++;
|
||||
walk++;
|
||||
while (*walk != '\0' && (*walk != '"' || *(walk-1) == '\\'))
|
||||
walk++;
|
||||
} else {
|
||||
if (token->name[0] == 's') {
|
||||
/* For a string (starting with 's'), the delimiters are
|
||||
* comma (,) and semicolon (;) which introduce a new
|
||||
* operation or command, respectively. Also, newlines
|
||||
* end a command. */
|
||||
while (*walk != ';' && *walk != ',' &&
|
||||
*walk != '\0' && *walk != '\r' &&
|
||||
*walk != '\n')
|
||||
walk++;
|
||||
} else {
|
||||
/* For a word, the delimiters are white space (' ' or
|
||||
* '\t'), closing square bracket (]), comma (,) and
|
||||
* semicolon (;). */
|
||||
while (*walk != ' ' && *walk != '\t' &&
|
||||
*walk != ']' && *walk != ',' &&
|
||||
*walk != ';' && *walk != '\r' &&
|
||||
*walk != '\n' && *walk != '\0')
|
||||
walk++;
|
||||
}
|
||||
}
|
||||
if (walk != beginning) {
|
||||
char *str = scalloc(walk-beginning + 1);
|
||||
/* We copy manually to handle escaping of characters. */
|
||||
int inpos, outpos;
|
||||
for (inpos = 0, outpos = 0;
|
||||
inpos < (walk-beginning);
|
||||
inpos++, outpos++) {
|
||||
/* We only handle escaped double quotes to not break
|
||||
* backwards compatibility with people using \w in
|
||||
* regular expressions etc. */
|
||||
if (beginning[inpos] == '\\' && beginning[inpos+1] == '"')
|
||||
inpos++;
|
||||
str[outpos] = beginning[inpos];
|
||||
}
|
||||
if (token->identifier)
|
||||
push_string(token->identifier, str);
|
||||
/* If we are at the end of a quoted string, skip the ending
|
||||
* double quote. */
|
||||
if (*walk == '"')
|
||||
walk++;
|
||||
next_state(token);
|
||||
token_handled = true;
|
||||
break;
|
||||
}
|
||||
}
|
||||
|
||||
if (strcmp(token->name, "end") == 0) {
|
||||
if (*walk == '\0' || *walk == ',' || *walk == ';') {
|
||||
next_state(token);
|
||||
token_handled = true;
|
||||
/* To make sure we start with an appropriate matching
|
||||
* datastructure for commands which do *not* specify any
|
||||
* criteria, we re-initialize the criteria system after
|
||||
* every command. */
|
||||
// TODO: make this testable
|
||||
#ifndef TEST_PARSER
|
||||
if (*walk == '\0' || *walk == ';')
|
||||
cmd_criteria_init(¤t_match, &subcommand_output);
|
||||
#endif
|
||||
walk++;
|
||||
break;
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
if (!token_handled) {
|
||||
/* Figure out how much memory we will need to fill in the names of
|
||||
* all tokens afterwards. */
|
||||
int tokenlen = 0;
|
||||
for (c = 0; c < ptr->n; c++)
|
||||
tokenlen += strlen(ptr->array[c].name) + strlen("'', ");
|
||||
|
||||
/* Build up a decent error message. We include the problem, the
|
||||
* full input, and underline the position where the parser
|
||||
* currently is. */
|
||||
char *errormessage;
|
||||
char *possible_tokens = smalloc(tokenlen + 1);
|
||||
char *tokenwalk = possible_tokens;
|
||||
for (c = 0; c < ptr->n; c++) {
|
||||
token = &(ptr->array[c]);
|
||||
if (token->name[0] == '\'') {
|
||||
/* A literal is copied to the error message enclosed with
|
||||
* single quotes. */
|
||||
*tokenwalk++ = '\'';
|
||||
strcpy(tokenwalk, token->name + 1);
|
||||
tokenwalk += strlen(token->name + 1);
|
||||
*tokenwalk++ = '\'';
|
||||
} else {
|
||||
/* Any other token is copied to the error message enclosed
|
||||
* with angle brackets. */
|
||||
*tokenwalk++ = '<';
|
||||
strcpy(tokenwalk, token->name);
|
||||
tokenwalk += strlen(token->name);
|
||||
*tokenwalk++ = '>';
|
||||
}
|
||||
if (c < (ptr->n - 1)) {
|
||||
*tokenwalk++ = ',';
|
||||
*tokenwalk++ = ' ';
|
||||
}
|
||||
}
|
||||
*tokenwalk = '\0';
|
||||
sasprintf(&errormessage, "Expected one of these tokens: %s",
|
||||
possible_tokens);
|
||||
free(possible_tokens);
|
||||
|
||||
/* Contains the same amount of characters as 'input' has, but with
|
||||
* the unparseable part highlighted using ^ characters. */
|
||||
char *position = smalloc(len + 1);
|
||||
for (const char *copywalk = input; *copywalk != '\0'; copywalk++)
|
||||
position[(copywalk - input)] = (copywalk >= walk ? '^' : ' ');
|
||||
position[len] = '\0';
|
||||
|
||||
ELOG("%s\n", errormessage);
|
||||
ELOG("Your command: %s\n", input);
|
||||
ELOG(" %s\n", position);
|
||||
|
||||
/* Format this error message as a JSON reply. */
|
||||
y(map_open);
|
||||
ystr("success");
|
||||
y(bool, false);
|
||||
/* We set parse_error to true to distinguish this from other
|
||||
* errors. i3-nagbar is spawned upon keypresses only for parser
|
||||
* errors. */
|
||||
ystr("parse_error");
|
||||
y(bool, true);
|
||||
ystr("error");
|
||||
ystr(errormessage);
|
||||
ystr("input");
|
||||
ystr(input);
|
||||
ystr("errorposition");
|
||||
ystr(position);
|
||||
y(map_close);
|
||||
|
||||
free(position);
|
||||
free(errormessage);
|
||||
clear_stack();
|
||||
break;
|
||||
}
|
||||
}
|
||||
|
||||
y(array_close);
|
||||
|
||||
return &command_output;
|
||||
}
|
||||
|
||||
/*******************************************************************************
|
||||
* Code for building the stand-alone binary test.commands_parser which is used
|
||||
* by t/187-commands-parser.t.
|
||||
******************************************************************************/
|
||||
|
||||
#ifdef TEST_PARSER
|
||||
|
||||
/*
|
||||
* Logs the given message to stdout while prefixing the current time to it,
|
||||
* but only if debug logging was activated.
|
||||
* This is to be called by DLOG() which includes filename/linenumber
|
||||
*
|
||||
*/
|
||||
void debuglog(char *fmt, ...) {
|
||||
va_list args;
|
||||
|
||||
va_start(args, fmt);
|
||||
fprintf(stdout, "# ");
|
||||
vfprintf(stdout, fmt, args);
|
||||
va_end(args);
|
||||
}
|
||||
|
||||
void errorlog(char *fmt, ...) {
|
||||
va_list args;
|
||||
|
||||
va_start(args, fmt);
|
||||
vfprintf(stderr, fmt, args);
|
||||
va_end(args);
|
||||
}
|
||||
|
||||
int main(int argc, char *argv[]) {
|
||||
if (argc < 2) {
|
||||
fprintf(stderr, "Syntax: %s <command>\n", argv[0]);
|
||||
return 1;
|
||||
}
|
||||
parse_config(argv[1]);
|
||||
}
|
||||
#endif
|
||||
Reference in New Issue
Block a user