Compare commits

..

4 Commits

Author SHA1 Message Date
d284a7edc8 Update .gitignore 2023-07-02 19:29:44 +01:00
9a686a2692 Add the json parser 2023-07-02 19:29:32 +01:00
10f1d5686e Update the compilation process 2023-07-02 19:29:05 +01:00
50f881c655 Reorganise the project 2023-07-02 19:28:48 +01:00
16 changed files with 1956 additions and 66 deletions

View File

@ -4,4 +4,4 @@ count_and_distances
pairs.json
main
genhavr
jsonparse
prochavr

View File

@ -1,16 +1,22 @@
#!/bin/bash
CC=clang++
CC=clang
CXX=clang++
CFLAGS="-g -Wall -Wextra -Iinclude"
# generator
GENSRC="./src/argparser.cpp ./src/generator.cpp ./src/haversine.cpp ./src/point_types.cpp ./src/genmain.cpp"
GENSRC="./src/generator/gen_argparser.cpp ./src/generator/generator.cpp ./src/haversine.cpp ./src/point_types.cpp ./src/generator/main.cpp"
GENOUT=genhavr
(set -x ; $CC $CFLAGS $GENSRC -o $GENOUT)
(set -x ; $CXX $CFLAGS $GENSRC -o $GENOUT)
# json parser
JSONSRC="./src/jsonparse.cpp"
JSONOUT=jsonparse
# processor
JSONSRC="./src/json/*.c"
JSONFLAGS="-c"
PROCSRC="./*.o ./src/haversine.cpp ./src/point_types.cpp ./src/processor/proc_argparser.cpp ./src/processor/main.cpp"
PROCOUT=prochavr
(set -x ; $CC $CFLAGS $JSONSRC -o $JSONOUT)
(set -x ; $CC $CFLAGS $JSONFLAGS $JSONSRC)
(set -x ; $CXX $CFLAGS $PROCSRC -o $PROCOUT)
rm ./*.o

View File

@ -1,5 +1,5 @@
#ifndef ARGPARSER_H
#define ARGPARSER_H
#ifndef GEN_ARGPARSER_H
#define GEN_ARGPARSER_H
#include "aliases.h"
#include <argp.h>
@ -12,4 +12,4 @@ struct GeneratorArgs {
GeneratorArgs parse_args(i32 argc, char *argv[]);
#endif // !ARGPARSER_H
#endif // !GEN_ARGPARSER_H

View File

@ -0,0 +1,30 @@
#ifndef DSTRING_H
#define DSTRING_H
#include "aliases.h"
#ifdef __cplusplus
extern "C" {
#endif
typedef struct dstring dstr_t;
dstr_t *dstr_with_capacity(u64 capacity);
dstr_t *dstr_from_string(const char *str);
void dstr_update(dstr_t **dst, const char *src);
void dstr_free(dstr_t **str);
void dstr_concat(dstr_t **dst, const char *src);
void dstr_append(dstr_t **dst, char c);
void dstr_resize(dstr_t **str);
void dstr_clear(dstr_t *str);
void dstr_print(const dstr_t *str);
i64 dstr_find(const dstr_t *str, const char *substr);
u64 dstr_length(const dstr_t *str);
u64 dstr_capacity(const dstr_t *str);
const char *dstr_to_cstr(const dstr_t *str);
#ifdef __cplusplus
}
#endif
#endif // !DSTRING_H

View File

@ -0,0 +1,82 @@
#ifndef JSON_ENTITIES_H
#define JSON_ENTITIES_H
#include "aliases.h"
#include "dstring.h"
#include <stdbool.h>
#ifdef __cplusplus
extern "C" {
#endif
typedef struct json_entity jentity_t;
typedef struct json_collection jcoll_t;
typedef struct json_value jval_t;
typedef struct json_pair jpair_t;
typedef enum {
JVAL_EMPTY,
JVAL_COLLECTION,
JVAL_STRING,
JVAL_INTEGER,
JVAL_DOUBLE,
JVAL_BOOLEAN,
JVAL_NULL,
} jval_type;
struct json_value {
jval_type type;
union {
void *null_val;
jcoll_t *collection;
dstr_t *string;
i64 num_int;
f64 num_dbl;
bool boolean;
};
};
struct json_pair {
dstr_t *key;
jval_t value;
};
typedef enum {
JENTITY_SINGLE,
JENTITY_PAIR,
} jentity_type;
struct json_entity {
jentity_type type;
union {
jval_t value;
jpair_t pair;
};
jentity_t *parent;
jentity_t *next;
};
typedef enum {
JCOLL_OBJECT,
JCOLL_ARRAY,
} jcoll_type;
struct json_collection {
u64 size;
jcoll_type type;
jentity_t *begin;
jentity_t *end;
};
void print_json(const jentity_t *entity, u32 indent);
void free_json(jentity_t **entity);
jcoll_t *get_collection_from_entity(const jentity_t *entity);
jentity_t *create_new_single_entity(const jval_t value, jentity_t *parent);
jentity_t *create_new_pair_entity(dstr_t *key, const jval_t value,
jentity_t *parent);
#ifdef __cplusplus
}
#endif
#endif // !JSON_ENTITIES_H

View File

@ -0,0 +1,72 @@
#ifndef LEXER_STATES_H
#define LEXER_STATES_H
#include "aliases.h"
#include <stdbool.h>
#define VALID_JSON true
#define INVALID_JSON false
#ifdef __cplusplus
extern "C" {
#endif
typedef const char *str_view_t;
typedef enum {
TK_NO_TOKEN,
TK_L_BRACE,
TK_R_BRACE,
TK_L_BRACKET,
TK_R_BRACKET,
TK_NULL,
TK_BOOL,
TK_STR_KEY,
TK_STR_VAL,
TK_INTEGER,
TK_DOUBLE,
} token_type;
typedef union {
void *no_val;
i64 num_int;
f64 num_frac;
str_view_t string;
bool boolean;
} token_value_t;
typedef struct {
u64 line;
u64 column;
token_type type;
token_value_t value;
} token_t;
typedef enum {
LEX_ERR_NONE,
LEX_ERR_INVALID,
} lex_err_type;
typedef struct {
lex_err_type errno;
str_view_t msg;
} lex_err_t;
typedef struct {
lex_err_t error;
token_t token;
} lex_result_t;
typedef struct lexer_s lexer_t;
void lexer_init(lexer_t **lexer);
void lexer_free(lexer_t **lexer);
lex_result_t get_next_token(lexer_t *lexer, const char *text);
void print_token(token_t token);
#ifdef __cplusplus
}
#endif
#endif // !LEXER_STATES_H

View File

@ -0,0 +1,19 @@
#ifndef PARSER_H
#define PARSER_H
#include "json_entities.h"
#include "lexer.h"
#ifdef __cplusplus
extern "C" {
#endif
typedef struct parser_s parser_t;
jentity_t *load_json(const char *filepath);
#ifdef __cplusplus
}
#endif
#endif // !PARSER_H

View File

@ -1,15 +1,16 @@
#include "argparser.h"
#include "generator/gen_argparser.h"
#include "aliases.h"
#include <argp.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <time.h>
static error_t argp_parser(i32 key, char *arg, argp_state *state);
INTERNAL error_t argp_parser(i32 key, char *arg, argp_state *state);
static argp parser = {};
INTERNAL argp parser = {};
static argp_option options[] = {
INTERNAL argp_option options[] = {
{.name = "seed", .key = 's', .arg = "SEED"},
{.name = "cluster", .key = 'c'},
{0, 0, 0, 0, 0, 0},

View File

@ -1,4 +1,4 @@
#include "generator.h"
#include "generator/generator.h"
#include "aliases.h"
#include "point_types.h"
#include <math.h>

View File

@ -1,11 +1,10 @@
#include "aliases.h"
#include "argparser.h"
#include "generator.h"
#include "generator/gen_argparser.h"
#include "generator/generator.h"
#include "haversine.h"
#include "point_types.h"
#include <stdio.h>
#include <stdlib.h>
#include <time.h>
#define EARTH_RADIUS_KM 6371.0

View File

@ -0,0 +1,211 @@
#include "json/dstring.h"
#include "aliases.h"
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
// Use this scalar to allocate extra memory in order to avoid having to
// constantly reallocate
#define CAPACITY_SCALAR 8
struct dstring {
u64 capacity;
u64 size;
char buf[];
};
dstr_t *dstr_with_capacity(u64 capacity) {
dstr_t *out = (dstr_t *)malloc(sizeof(dstr_t) + capacity + 1);
if (!out) {
return NULL;
}
out->capacity = capacity;
out->size = 0;
memset(out->buf, 0, capacity + 1);
return out;
}
dstr_t *dstr_from_string(const char *str) {
u64 length = strlen(str);
u64 capacity = length * CAPACITY_SCALAR;
dstr_t *out = dstr_with_capacity(capacity);
if (!out) {
return NULL;
}
out->size = length;
strncpy(out->buf, str, length);
return out;
}
void dstr_update(dstr_t **dst, const char *src) {
if (!(*dst)) {
return;
}
u64 length = strlen(src);
dstr_t *str = *dst;
if (length <= str->capacity) {
memset(str->buf, 0, str->capacity);
str->size = length;
strncpy(str->buf, src, length);
} else {
u64 capacity = length * CAPACITY_SCALAR;
dstr_t *tmp = (dstr_t *)realloc(*dst, sizeof(dstr_t) + capacity + 1);
if (!tmp) {
return;
}
tmp->capacity = capacity;
tmp->size = length;
strncpy(tmp->buf, src, length);
*dst = tmp;
}
}
void dstr_free(dstr_t **str) {
if (!(*str)) {
return;
}
free(*str);
*str = NULL;
}
void dstr_concat(dstr_t **dst, const char *src) {
if (!(*dst)) {
return;
}
u64 src_length = strlen(src);
if (src_length == 0) {
return;
}
u64 new_length = (*dst)->size + src_length;
char str[new_length + 1];
memset(str, 0, new_length + 1);
strncpy(str, (*dst)->buf, (*dst)->size);
strncat(str, src, src_length);
dstr_update(dst, str);
}
void dstr_append(dstr_t **dst, char c) {
if (!(*dst)) {
return;
}
u64 new_length = (*dst)->size + 1;
char str[new_length + 1];
memset(str, 0, new_length + 1);
strncpy(str, (*dst)->buf, (*dst)->size);
str[(*dst)->size] = c;
dstr_update(dst, str);
}
void dstr_resize(dstr_t **str) {
u64 capacity = (*str)->size;
dstr_t *tmp = (dstr_t *)realloc(*str, sizeof(dstr_t) + capacity + 1);
if (!tmp) {
return;
}
tmp->capacity = capacity;
*str = tmp;
}
void dstr_clear(dstr_t *str) {
if (!str || str->size == 0) {
return;
}
memset(str->buf, 0, str->capacity);
str->size = 0;
}
void dstr_print(const dstr_t *str) {
if (!str) {
return;
}
printf("%s\n", str->buf);
}
i64 dstr_find(const dstr_t *str, const char *substr) {
if (!str || !substr) {
return -1;
}
u64 substr_length = strlen(substr);
if (substr_length == 0 || substr_length > str->size) {
return -1;
}
char buf[substr_length + 1];
memset(buf, 0, substr_length + 1);
for (u64 i = 0; i < str->size; ++i) {
if (i + substr_length >= str->size) {
break;
}
for (u64 j = 0; j < substr_length; ++j) {
buf[j] = str->buf[i + j];
}
if (strcmp(buf, substr) == 0) {
return i;
}
}
return -1;
}
u64 dstr_length(const dstr_t *str) {
if (!str) {
return 0;
}
return str->size;
}
u64 dstr_capacity(const dstr_t *str) {
if (!str) {
return 0;
}
return str->capacity;
}
const char *dstr_to_cstr(const dstr_t *str) {
if (!str) {
return "";
}
return str->buf;
}

View File

@ -0,0 +1,194 @@
#include "json/json_entities.h"
#include "aliases.h"
#include "json/dstring.h"
#include <stdio.h>
#include <stdlib.h>
void print_json(const jentity_t *entity, u32 indent) {
PERSISTENT i32 indentation = 0;
dstr_t *key = NULL;
const jval_t *value = NULL;
if (entity->type == JENTITY_SINGLE) {
value = &(entity->value);
} else {
key = entity->pair.key;
value = &(entity->pair.value);
}
if (key) {
printf("%*s\"%s\": ", indentation * indent, "", dstr_to_cstr(key));
}
switch (value->type) {
case JVAL_COLLECTION: {
const char *open = "";
const char *close = "";
if (value->collection->type == JCOLL_OBJECT) {
open = "{";
close = "}";
} else {
open = "[";
close = "]";
}
if (key) {
printf("%s\n", open);
} else {
printf("%*s%s\n", indentation * indent, "", open);
}
++indentation;
if (value->collection->begin) {
print_json(value->collection->begin, indent);
}
--indentation;
printf("\n%*s%s", indentation * indent, "", close);
break;
}
case JVAL_STRING:
if (key) {
printf("\"%s\"", dstr_to_cstr(value->string));
} else {
printf("%*s\"%s\"", indentation * indent, "",
dstr_to_cstr(value->string));
}
break;
case JVAL_INTEGER:
if (key) {
printf("%llu", (unsigned long long)value->num_int);
} else {
printf("%*s%llu", indentation * indent, "",
(unsigned long long)value->num_int);
}
break;
case JVAL_DOUBLE:
if (key) {
printf("%f", value->num_dbl);
} else {
printf("%*s%f", indentation * indent, "", value->num_dbl);
}
break;
case JVAL_BOOLEAN:
if (key) {
printf("%s", value->boolean ? "true" : "false");
} else {
printf("%*s%s", indentation * indent, "",
value->boolean ? "true" : "false");
}
break;
case JVAL_NULL:
if (key) {
printf("%s", "null");
} else {
printf("%*s%s", indentation * indent, "", "null");
}
break;
case JVAL_EMPTY:
break;
}
if (entity->next) {
printf(",\n");
print_json(entity->next, indent);
}
// Add newline after printing the entire json tree
if (indentation == 0 && entity->parent == NULL && entity->next == NULL) {
printf("\n");
}
}
void free_json(jentity_t **entity) {
if (!(*entity)) {
return;
}
jentity_t *entt_ptr = *entity;
dstr_t *key = NULL;
const jval_t *value = NULL;
if (entt_ptr->type == JENTITY_SINGLE) {
value = &(entt_ptr->value);
} else {
key = entt_ptr->pair.key;
value = &(entt_ptr->pair.value);
}
if (key) {
dstr_free(&(entt_ptr->pair.key));
}
switch (value->type) {
case JVAL_COLLECTION:
if (value->collection->begin) {
free_json(&(value->collection->begin));
}
free(value->collection);
break;
case JVAL_STRING:
dstr_free(&(entt_ptr->pair.value.string));
break;
default:
break;
}
if (entt_ptr->next) {
free_json(&(entt_ptr->next));
}
free(*entity);
*entity = NULL;
}
jcoll_t *get_collection_from_entity(const jentity_t *entity) {
return entity->type == JENTITY_SINGLE ? entity->value.collection
: entity->pair.value.collection;
}
jentity_t *create_new_single_entity(const jval_t value, jentity_t *parent) {
jentity_t *entity = (jentity_t *)malloc(sizeof(jentity_t));
if (!entity) {
return NULL;
}
entity->type = JENTITY_SINGLE;
entity->value = value;
entity->parent = parent;
entity->next = NULL;
return entity;
}
jentity_t *create_new_pair_entity(dstr_t *key, const jval_t value,
jentity_t *parent) {
jentity_t *entity = (jentity_t *)malloc(sizeof(jentity_t));
if (!entity) {
return NULL;
}
entity->type = JENTITY_PAIR;
entity->pair.key = key;
entity->pair.value = value;
entity->parent = parent;
entity->next = NULL;
return entity;
}

File diff suppressed because it is too large Load Diff

View File

@ -0,0 +1,256 @@
#include "json/parser.h"
#include "aliases.h"
#include "json/dstring.h"
#include "json/json_entities.h"
#include "json/lexer.h"
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
struct parser_s {
jentity_t *root;
jentity_t *current;
jval_t value;
};
INTERNAL void parser_free(parser_t **parser);
INTERNAL void parser_init(parser_t **parser);
INTERNAL void parse_token(parser_t *parser, token_t token);
INTERNAL void add_key(parser_t *parser, dstr_t *key);
INTERNAL jentity_t *add_value(parser_t *parser);
INTERNAL void add_collection(parser_t *parser);
jentity_t *load_json(const char *filepath) {
FILE *fp = fopen(filepath, "r");
if (!fp) {
return NULL;
}
fseek(fp, 0, SEEK_END);
u64 length = ftell(fp);
fseek(fp, 0, SEEK_SET);
char json[length + 1];
memset(json, 0, length + 1);
fread(json, sizeof(char), length, fp);
fclose(fp);
lexer_t *lexer = NULL;
parser_t *parser = NULL;
lexer_init(&lexer);
if (!lexer) {
return NULL;
}
parser_init(&parser);
if (!parser) {
lexer_free(&lexer);
return NULL;
}
lex_result_t result = get_next_token(lexer, json);
if (result.error.errno) {
printf("%s\n", result.error.msg);
} else {
while (result.token.type != TK_NO_TOKEN) {
parse_token(parser, result.token);
result = get_next_token(lexer, NULL);
if (result.error.errno) {
printf("%s\n", result.error.msg);
break;
}
}
}
jentity_t *root = parser->root;
parser_free(&parser);
lexer_free(&lexer);
return root;
}
void parser_init(parser_t **parser) {
if (*parser) {
parser_free(parser);
}
*parser = (parser_t *)malloc(sizeof(parser_t));
if (!(*parser)) {
return;
}
(*parser)->root = NULL;
(*parser)->current = NULL;
(*parser)->value = (jval_t){};
}
void parser_free(parser_t **parser) {
if (!(*parser)) {
return;
}
(*parser)->root = NULL;
(*parser)->current = NULL;
free(*parser);
*parser = NULL;
}
void parse_token(parser_t *parser, token_t token) {
switch (token.type) {
case TK_L_BRACE:
case TK_L_BRACKET: {
parser->value = (jval_t){
.type = JVAL_COLLECTION,
.collection = (jcoll_t *)malloc(sizeof(jcoll_t)),
};
if (token.type == TK_L_BRACE) {
parser->value.collection->type = JCOLL_OBJECT;
} else {
parser->value.collection->type = JCOLL_ARRAY;
}
parser->value.collection->size = 0;
parser->value.collection->begin = NULL;
parser->value.collection->end = NULL;
add_collection(parser);
break;
}
case TK_R_BRACE:
case TK_R_BRACKET:
if (parser->current->parent) {
parser->current = parser->current->parent;
}
break;
case TK_STR_KEY: {
parser->value = (jval_t){.type = JVAL_EMPTY, .null_val = NULL};
add_key(parser, dstr_from_string(token.value.string));
break;
}
case TK_NULL: {
parser->value = (jval_t){.type = JVAL_NULL, .null_val = NULL};
add_value(parser);
break;
}
case TK_BOOL: {
parser->value =
(jval_t){.type = JVAL_BOOLEAN, .boolean = token.value.boolean};
add_value(parser);
break;
}
case TK_STR_VAL: {
parser->value = (jval_t){.type = JVAL_STRING,
.string = dstr_from_string(token.value.string)};
add_value(parser);
break;
}
case TK_INTEGER: {
parser->value =
(jval_t){.type = JVAL_INTEGER, .num_int = token.value.num_int};
add_value(parser);
break;
}
case TK_DOUBLE: {
parser->value =
(jval_t){.type = JVAL_DOUBLE, .num_dbl = token.value.num_frac};
add_value(parser);
break;
}
case TK_NO_TOKEN:
break;
}
}
void add_key(parser_t *parser, dstr_t *key) {
jcoll_t *collection = get_collection_from_entity(parser->current);
if (!collection) {
return;
}
if (!(collection->end)) {
collection->begin = collection->end =
create_new_pair_entity(key, parser->value, parser->current);
collection->size = 1;
} else {
jentity_t *new_entity =
create_new_pair_entity(key, parser->value, parser->current);
collection->end->next = new_entity;
collection->end = new_entity;
++(collection->size);
}
}
jentity_t *add_value(parser_t *parser) {
jcoll_t *collection = get_collection_from_entity(parser->current);
if (!collection) {
return NULL;
}
if (!(collection->end)) {
collection->begin = collection->end =
create_new_single_entity(parser->value, parser->current);
collection->size = 1;
} else {
if (collection->end->type == JENTITY_PAIR &&
collection->end->pair.value.type == JVAL_EMPTY) {
collection->end->pair.value = parser->value;
} else {
jentity_t *new_entity =
create_new_single_entity(parser->value, parser->current);
collection->end->next = new_entity;
collection->end = new_entity;
++(collection->size);
}
}
return collection->end;
}
void add_collection(parser_t *parser) {
if (!(parser->root)) {
parser->root = parser->current =
create_new_single_entity(parser->value, NULL);
return;
}
parser->current = add_value(parser);
}

View File

@ -1,47 +0,0 @@
#include "aliases.h"
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
i32 main(i32 argc, char *argv[]) {
if (argc < 2) {
printf("Missing filename\n");
return EXIT_FAILURE;
}
const char *filename = argv[1];
FILE *fp = fopen(filename, "r");
if (!fp) {
printf("Failed to open file: %s\n", filename);
return EXIT_FAILURE;
}
fseek(fp, 0, SEEK_END);
u64 length = ftell(fp);
fseek(fp, 0, SEEK_SET);
char text[length + 1];
memset(text, 0, length);
fread(text, sizeof(char), length, fp);
text[length] = '\0';
const char *delim = ", \t\n";
char *token = strtok(text, delim);
while (token) {
printf("TOKEN: %s\n", token);
token = strtok(NULL, delim);
}
fclose(fp);
return EXIT_SUCCESS;
}