diff options
Diffstat (limited to 'src')
| -rw-r--r-- | src/dump.c | 199 | ||||
| -rw-r--r-- | src/jansson.h | 5 | ||||
| -rw-r--r-- | src/load.c | 11 | ||||
| -rw-r--r-- | src/utf.c | 39 | ||||
| -rw-r--r-- | src/utf.h | 3 |
5 files changed, 205 insertions, 52 deletions
@@ -9,10 +9,13 @@ #include <stdio.h> #include <stdlib.h> #include <string.h> +#include <stdint.h> +#include <assert.h> #include <jansson.h> #include "jansson_private.h" #include "strbuffer.h" +#include "utf.h" #define MAX_INTEGER_STR_LENGTH 100 #define MAX_REAL_STR_LENGTH 100 @@ -42,7 +45,7 @@ static int dump_to_file(const char *buffer, int size, void *data) /* 256 spaces (the maximum indentation size) */ static char whitespace[] = " "; -static int dump_indent(unsigned long flags, int depth, dump_func dump, void *data) +static int dump_indent(unsigned long flags, int depth, int space, dump_func dump, void *data) { if(JSON_INDENT(flags) > 0) { @@ -57,37 +60,56 @@ static int dump_indent(unsigned long flags, int depth, dump_func dump, void *dat return -1; } } + else if(space && !(flags & JSON_COMPACT)) + { + return dump(" ", 1, data); + } return 0; } -static int dump_string(const char *str, dump_func dump, void *data) +static int dump_string(const char *str, int ascii, dump_func dump, void *data) { - const char *end; + const char *pos, *end; + int32_t codepoint; if(dump("\"", 1, data)) return -1; - end = str; + end = pos = str; while(1) { const char *text; - char seq[7]; + char seq[13]; int length; - while(*end && *end != '\\' && *end != '"' && (unsigned char)*end > 0x1F) - end++; + while(*end) + { + end = utf8_iterate(pos, &codepoint); + if(!end) + return -1; + + /* mandatory escape or control char */ + if(codepoint == '\\' || codepoint == '"' || codepoint < 0x20) + break; + + /* non-ASCII */ + if(ascii && codepoint > 0x7F) + break; + + pos = end; + } - if(end != str) { - if(dump(str, end - str, data)) + if(pos != str) { + if(dump(str, pos - str, data)) return -1; } - if(!*end) + if(end == pos) break; /* handle \, ", and control codes */ length = 2; - switch(*end) + switch(codepoint) { case '\\': text = "\\\\"; break; case '\"': text = "\\\""; break; @@ -98,9 +120,27 @@ static int dump_string(const char *str, dump_func dump, void *data) case '\t': text = "\\t"; break; default: { - sprintf(seq, "\\u00%02x", *end); + /* codepoint is in BMP */ + if(codepoint < 0x10000) + { + sprintf(seq, "\\u%04x", codepoint); + length = 6; + } + + /* not in BMP -> construct a UTF-16 surrogate pair */ + else + { + int32_t first, last; + + codepoint -= 0x10000; + first = 0xD800 | ((codepoint & 0xffc00) >> 10); + last = 0xDC00 | (codepoint & 0x003ff); + + sprintf(seq, "\\u%04x\\u%04x", first, last); + length = 12; + } + text = seq; - length = 6; break; } } @@ -108,16 +148,22 @@ static int dump_string(const char *str, dump_func dump, void *data) if(dump(text, length, data)) return -1; - end++; - str = end; + str = pos = end; } return dump("\"", 1, data); } +static int object_key_cmp(const void *key1, const void *key2) +{ + return strcmp(*(const char **)key1, *(const char **)key2); +} + static int do_dump(const json_t *json, unsigned long flags, int depth, dump_func dump, void *data) { + int ascii = flags & JSON_ENSURE_ASCII ? 1 : 0; + switch(json_typeof(json)) { case JSON_NULL: return dump("null", 4, data); @@ -168,7 +214,7 @@ static int do_dump(const json_t *json, unsigned long flags, int depth, } case JSON_STRING: - return dump_string(json_string_value(json), dump, data); + return dump_string(json_string_value(json), ascii, dump, data); case JSON_ARRAY: { @@ -188,7 +234,7 @@ static int do_dump(const json_t *json, unsigned long flags, int depth, return -1; if(n == 0) return dump("]", 1, data); - if(dump_indent(flags, depth + 1, dump, data)) + if(dump_indent(flags, depth + 1, 0, dump, data)) return -1; for(i = 0; i < n; ++i) { @@ -199,12 +245,12 @@ static int do_dump(const json_t *json, unsigned long flags, int depth, if(i < n - 1) { if(dump(",", 1, data) || - dump_indent(flags, depth + 1, dump, data)) + dump_indent(flags, depth + 1, 1, dump, data)) return -1; } else { - if(dump_indent(flags, depth, dump, data)) + if(dump_indent(flags, depth, 0, dump, data)) return -1; } } @@ -217,6 +263,17 @@ static int do_dump(const json_t *json, unsigned long flags, int depth, { json_object_t *object; void *iter; + const char *separator; + int separator_length; + + if(flags & JSON_COMPACT) { + separator = ":"; + separator_length = 1; + } + else { + separator = ": "; + separator_length = 2; + } /* detect circular references */ object = json_to_object(json); @@ -230,32 +287,99 @@ static int do_dump(const json_t *json, unsigned long flags, int depth, return -1; if(!iter) return dump("}", 1, data); - if(dump_indent(flags, depth + 1, dump, data)) + if(dump_indent(flags, depth + 1, 0, dump, data)) return -1; - while(iter) + if(flags & JSON_SORT_KEYS) { - void *next = json_object_iter_next((json_t *)json, iter); + /* Sort keys */ - dump_string(json_object_iter_key(iter), dump, data); - if(dump(": ", 2, data) || - do_dump(json_object_iter_value(iter), flags, depth + 1, - dump, data)) + const char **keys; + unsigned int size; + unsigned int i; + + size = json_object_size(json); + keys = malloc(size * sizeof(const char *)); + if(!keys) return -1; - if(next) + i = 0; + while(iter) { - if(dump(",", 1, data) || - dump_indent(flags, depth + 1, dump, data)) - return -1; + keys[i] = json_object_iter_key(iter); + iter = json_object_iter_next((json_t *)json, iter); + i++; } - else + assert(i == size); + + qsort(keys, size, sizeof(const char *), object_key_cmp); + + for(i = 0; i < size; i++) { - if(dump_indent(flags, depth, dump, data)) + const char *key; + json_t *value; + + key = keys[i]; + value = json_object_get(json, key); + assert(value); + + dump_string(key, ascii, dump, data); + if(dump(separator, separator_length, data) || + do_dump(value, flags, depth + 1, dump, data)) + { + free(keys); return -1; + } + + if(i < size - 1) + { + if(dump(",", 1, data) || + dump_indent(flags, depth + 1, 1, dump, data)) + { + free(keys); + return -1; + } + } + else + { + if(dump_indent(flags, depth, 0, dump, data)) + { + free(keys); + return -1; + } + } } - iter = next; + free(keys); + } + else + { + /* Don't sort keys */ + + while(iter) + { + void *next = json_object_iter_next((json_t *)json, iter); + + dump_string(json_object_iter_key(iter), ascii, dump, data); + if(dump(separator, separator_length, data) || + do_dump(json_object_iter_value(iter), flags, depth + 1, + dump, data)) + return -1; + + if(next) + { + if(dump(",", 1, data) || + dump_indent(flags, depth + 1, 1, dump, data)) + return -1; + } + else + { + if(dump_indent(flags, depth, 0, dump, data)) + return -1; + } + + iter = next; + } } object->visited = 0; @@ -285,11 +409,6 @@ char *json_dumps(const json_t *json, unsigned long flags) return NULL; } - if(dump_to_strbuffer("\n", 1, (void *)&strbuff)) { - strbuffer_close(&strbuff); - return NULL; - } - result = strdup(strbuffer_value(&strbuff)); strbuffer_close(&strbuff); @@ -301,9 +420,7 @@ int json_dumpf(const json_t *json, FILE *output, unsigned long flags) if(!json_is_array(json) && !json_is_object(json)) return -1; - if(do_dump(json, flags, 0, dump_to_file, (void *)output)) - return -1; - return dump_to_file("\n", 1, (void *)output); + return do_dump(json, flags, 0, dump_to_file, (void *)output); } int json_dump_file(const json_t *json, const char *path, unsigned long flags) diff --git a/src/jansson.h b/src/jansson.h index ac6736f..607dfb5 100644 --- a/src/jansson.h +++ b/src/jansson.h @@ -141,7 +141,10 @@ json_t *json_loads(const char *input, json_error_t *error); json_t *json_loadf(FILE *input, json_error_t *error); json_t *json_load_file(const char *path, json_error_t *error); -#define JSON_INDENT(n) (n & 0xFF) +#define JSON_INDENT(n) (n & 0xFF) +#define JSON_COMPACT 0x100 +#define JSON_ENSURE_ASCII 0x200 +#define JSON_SORT_KEYS 0x400 char *json_dumps(const json_t *json, unsigned long flags); int json_dumpf(const json_t *json, FILE *output, unsigned long flags); @@ -14,6 +14,7 @@ #include <string.h> #include <stdarg.h> #include <assert.h> +#include <stdint.h> #include <jansson.h> #include "jansson_private.h" @@ -148,7 +149,7 @@ static char stream_get(stream_t *stream, json_error_t *error) for(i = 1; i < count; i++) stream->buffer[i] = stream->get(stream->data); - if(!utf8_check_full(stream->buffer, count)) + if(!utf8_check_full(stream->buffer, count, NULL)) goto out; stream->stream_pos += count; @@ -221,10 +222,10 @@ static void lex_save_cached(lex_t *lex) } /* assumes that str points to 'u' plus at least 4 valid hex digits */ -static int decode_unicode_escape(const char *str) +static int32_t decode_unicode_escape(const char *str) { int i; - int value = 0; + int32_t value = 0; assert(str[0] == 'u'); @@ -325,7 +326,7 @@ static void lex_scan_string(lex_t *lex, json_error_t *error) if(*p == 'u') { char buffer[4]; int length; - int value; + int32_t value; value = decode_unicode_escape(p); p += 5; @@ -333,7 +334,7 @@ static void lex_scan_string(lex_t *lex, json_error_t *error) if(0xD800 <= value && value <= 0xDBFF) { /* surrogate pair */ if(*p == '\\' && *(p + 1) == 'u') { - int value2 = decode_unicode_escape(++p); + int32_t value2 = decode_unicode_escape(++p); p += 5; if(0xDC00 <= value2 && value2 <= 0xDFFF) { @@ -6,8 +6,9 @@ */ #include <string.h> +#include <stdint.h> -int utf8_encode(int codepoint, char *buffer, int *size) +int utf8_encode(int32_t codepoint, char *buffer, int *size) { if(codepoint < 0) return -1; @@ -79,9 +80,10 @@ int utf8_check_first(char byte) } } -int utf8_check_full(const char *buffer, int size) +int utf8_check_full(const char *buffer, int size, int32_t *codepoint) { - int i, value = 0; + int i; + int32_t value = 0; unsigned char u = (unsigned char)buffer[0]; if(size == 2) @@ -128,9 +130,38 @@ int utf8_check_full(const char *buffer, int size) return 0; } + if(codepoint) + *codepoint = value; + return 1; } +const char *utf8_iterate(const char *buffer, int32_t *codepoint) +{ + int count; + int32_t value; + + if(!*buffer) + return buffer; + + count = utf8_check_first(buffer[0]); + if(count <= 0) + return NULL; + + if(count == 1) + value = (unsigned char)buffer[0]; + else + { + if(!utf8_check_full(buffer, count, &value)) + return NULL; + } + + if(codepoint) + *codepoint = value; + + return buffer + count; +} + int utf8_check_string(const char *string, int length) { int i; @@ -148,7 +179,7 @@ int utf8_check_string(const char *string, int length) if(i + count > length) return 0; - if(!utf8_check_full(&string[i], count)) + if(!utf8_check_full(&string[i], count, NULL)) return 0; i += count - 1; @@ -11,7 +11,8 @@ int utf8_encode(int codepoint, char *buffer, int *size); int utf8_check_first(char byte); -int utf8_check_full(const char *buffer, int size); +int utf8_check_full(const char *buffer, int size, int32_t *codepoint); +const char *utf8_iterate(const char *buffer, int32_t *codepoint); int utf8_check_string(const char *string, int length); |