[LTP] [PATCH 1/1] docparse: Escape backslash, tab and double quote in JSON

[LTP] [PATCH 1/1] docparse: Escape backslash, tab and double quote in JSON

[Petr Vorel]

Signed-off-by: Petr Vorel <pvorel@suse.cz>
---
Hi,

not sure if I should escape more, e.g.:
\b  Backspace (ascii code 08)
\f  Form feed (ascii code 0C)
\n  New line
\r  Carriage return

Tested on Richard's BPF patchset [1], which got affected on " + previous
problems on CAN tests, which contained \t in testcases/network/can/filter-tests/can_filter.c
(i.e. with reverted 1cdf8ce8b).

Kind regards,
Petr

[1] https://patchwork.ozlabs.org/project/ltp/list/?series=240772&state=*
[2] https://patchwork.ozlabs.org/project/ltp/patch/20210426120107.6632-2-rpalethorpe@suse.com/

 docparse/data_storage.h | 36 ++++++++++++++++++++++++++++++++++--
 1 file changed, 34 insertions(+), 2 deletions(-)

diff --git a/docparse/data_storage.h b/docparse/data_storage.h
index ef420c08f..08cdc009d 100644
--- a/docparse/data_storage.h
+++ b/docparse/data_storage.h
@@ -256,14 +256,46 @@ static inline void data_fprintf(FILE *f, unsigned int padd, const char *fmt, ...
 	va_end(va);
 }
 
-static inline void data_to_json_(struct data_node *self, FILE *f, unsigned int padd, int do_padd)
+static inline void json_escape_(char str[], char search, char replace[])
+{
+	char *tmp;
+	char *p = str;
+	size_t i, str_len, tmp_len, replace_len, shift;
+
+	while ((tmp = strchr(p, search))) {
+		str_len = strlen(str);
+		tmp_len = strlen(tmp);
+		replace_len = strlen(replace);
+		shift = str_len - tmp_len;
+
+		memmove(str + shift + replace_len - 1, str + shift, tmp_len);
+
+		for (i = 0; i < replace_len; i++)
+			str[shift++] = replace[i];
+
+		str[str_len + replace_len - 1] = '\0';
+		p = tmp + replace_len;
+	}
+}
+
+static inline const char *json_escape(char *input)
+{
+	json_escape_(input, '\\', "\\\\");
+	json_escape_(input, '"', "\\\"");
+	json_escape_(input, '\t', "\\t");
+
+	return input;
+}
+
+static inline void data_to_json_(struct data_node *self, FILE *f, unsigned int
+				 padd, int do_padd)
 {
 	unsigned int i;
 
 	switch (self->type) {
 	case DATA_STRING:
 		padd = do_padd ? padd : 0;
-		data_fprintf(f, padd, "\"%s\"", self->string.val);
+		data_fprintf(f, padd, "\"%s\"", json_escape((self->string.val)));
 	break;
 	case DATA_HASH:
 		for (i = 0; i < self->hash.elems_used; i++) {
-- 
2.31.1

[LTP] [PATCH 1/1] docparse: Escape backslash, tab and double quote in JSON

[Cyril Hrubis]

Hi!
> not sure if I should escape more, e.g.:
> \b  Backspace (ascii code 08)
> \f  Form feed (ascii code 0C)
> \n  New line
> \r  Carriage return
> 
> Tested on Richard's BPF patchset [1], which got affected on " + previous
> problems on CAN tests, which contained \t in testcases/network/can/filter-tests/can_filter.c
> (i.e. with reverted 1cdf8ce8b).
> 
> Kind regards,
> Petr
> 
> [1] https://patchwork.ozlabs.org/project/ltp/list/?series=240772&state=*
> [2] https://patchwork.ozlabs.org/project/ltp/patch/20210426120107.6632-2-rpalethorpe@suse.com/
> 
>  docparse/data_storage.h | 36 ++++++++++++++++++++++++++++++++++--
>  1 file changed, 34 insertions(+), 2 deletions(-)
> 
> diff --git a/docparse/data_storage.h b/docparse/data_storage.h
> index ef420c08f..08cdc009d 100644
> --- a/docparse/data_storage.h
> +++ b/docparse/data_storage.h
> @@ -256,14 +256,46 @@ static inline void data_fprintf(FILE *f, unsigned int padd, const char *fmt, ...
>  	va_end(va);
>  }
>  
> -static inline void data_to_json_(struct data_node *self, FILE *f, unsigned int padd, int do_padd)
> +static inline void json_escape_(char str[], char search, char replace[])
> +{
> +	char *tmp;
> +	char *p = str;
> +	size_t i, str_len, tmp_len, replace_len, shift;
> +
> +	while ((tmp = strchr(p, search))) {
> +		str_len = strlen(str);
> +		tmp_len = strlen(tmp);
> +		replace_len = strlen(replace);
> +		shift = str_len - tmp_len;
> +
> +		memmove(str + shift + replace_len - 1, str + shift, tmp_len);
> +
> +		for (i = 0; i < replace_len; i++)
> +			str[shift++] = replace[i];
> +
> +		str[str_len + replace_len - 1] = '\0';
> +		p = tmp + replace_len;
> +	}
> +}
> +
> +static inline const char *json_escape(char *input)
> +{
> +	json_escape_(input, '\\', "\\\\");
> +	json_escape_(input, '"', "\\\"");
> +	json_escape_(input, '\t', "\\t");
> +
> +	return input;
> +}

I guess that it would be easier to write a function to print json
string, e.g.

static inline void data_fprintf_esc_(FILE *f, unsigned int padd, const char *str)
{
	while (padd-- > 0)
		fputc(' ', f);

	fputc('"', f);

	while (*str) {
		switch (*str) {
		case '\\':
			fputs("\\\\", f);
		break;
		case '"':
			fputs("\\\"", f);
		break;
		case '\t':
			fputs("\\t", f);
		break;
		default:
			putc(*str, f);
		break;
		}
		str++;
	}

	fputc('"', f);
}

> +static inline void data_to_json_(struct data_node *self, FILE *f, unsigned int
> +				 padd, int do_padd)
>  {
>  	unsigned int i;
>  
>  	switch (self->type) {
>  	case DATA_STRING:
>  		padd = do_padd ? padd : 0;
> -		data_fprintf(f, padd, "\"%s\"", self->string.val);
> +		data_fprintf(f, padd, "\"%s\"", json_escape((self->string.val)));
>  	break;
>  	case DATA_HASH:
>  		for (i = 0; i < self->hash.elems_used; i++) {
> -- 
> 2.31.1
> 

-- 
Cyril Hrubis
chrubis@suse.cz

[LTP] [PATCH 1/1] docparse: Escape backslash, tab and double quote in JSON

[Petr Vorel]

Hi Cyril,

> I guess that it would be easier to write a function to print json
> string, e.g.

> static inline void data_fprintf_esc_(FILE *f, unsigned int padd, const char *str)
> {
> 	while (padd-- > 0)
> 		fputc(' ', f);

> 	fputc('"', f);

> 	while (*str) {
> 		switch (*str) {
> 		case '\\':
> 			fputs("\\\\", f);
> 		break;
> 		case '"':
> 			fputs("\\\"", f);
> 		break;
> 		case '\t':
> 			fputs("\\t", f);
> 		break;
> 		default:
> 			putc(*str, f);
> 		break;
> 		}
> 		str++;
> 	}

> 	fputc('"', f);
> }

That's indeed much better, thanks! I'll send v2 with you as author.

Kind regards,
Petr