BLAHAJ
/
libsigrok
10
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

input/csv: improve reliabilty of text line isolation 

Slightly unobfuscate the "end of current input chunk" marker in the data
processing loop. Make the variable's identifier reflect that it's not a
temporary, but instead something worth keeping around until needed again.

Unbreak the calculation of line numbers in those situations where input
chunks (including previously accumulated unprocessed data) happens to
start with a line termination. This covers input files which start with
empty lines, as well as environments with mutli-byte line termination
sequences (CR/LF) and arbitrary distribution of bytes across chunks.

This fixes bug #968.

Accept when there is no line termination in the current input chunk. We
cannot assume that calling applications always provide file content in
large enough chunks to span complete lines. And any arbitrary chunk size
which applications happen to use can get exceeded by input files (e.g.
for generated files with wide data or long comments).
This commit is contained in:
Gerhard Sittig 2019-10-19 11:47:45 +02:00
parent cb3b80512e
commit fbefa03f58
1 changed files with 11 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

20
src/input/csv.c
View File

@ -1502,7 +1502,8 @@ static int process_buffer(struct sr_input *in, gboolean is_eof)
const struct column_details *details; const struct column_details *details;
col_parse_cb parse_func; col_parse_cb parse_func;
int ret; int ret;
char *p, **lines, *line, **columns, *column; char *processed_up_to;
char **lines, *line, **columns, *column;
inc = in->priv; inc = in->priv;
if (!inc->started) { if (!inc->started) {
@ -1526,16 +1527,17 @@ static int process_buffer(struct sr_input *in, gboolean is_eof)
if (!in->buf->len) if (!in->buf->len)
return SR_OK; return SR_OK;
if (is_eof) { if (is_eof) {
p = in->buf->str + in->buf->len; processed_up_to = in->buf->str + in->buf->len;
} else { } else {
p = g_strrstr_len(in->buf->str, in->buf->len, inc->termination); processed_up_to = g_strrstr_len(in->buf->str, in->buf->len,
if (!p) inc->termination);
return SR_ERR; if (!processed_up_to)
*p = '\0'; return SR_OK;
p += strlen(inc->termination); *processed_up_to = '\0';
processed_up_to += strlen(inc->termination);
} }
g_strstrip(in->buf->str);
/* Split input text lines and process their columns. */
ret = SR_OK; ret = SR_OK;
lines = g_strsplit(in->buf->str, inc->termination, 0); lines = g_strsplit(in->buf->str, inc->termination, 0);
for (line_idx = 0; (line = lines[line_idx]); line_idx++) { for (line_idx = 0; (line = lines[line_idx]); line_idx++) {
@ -1612,7 +1614,7 @@ static int process_buffer(struct sr_input *in, gboolean is_eof)
g_strfreev(columns); g_strfreev(columns);
} }
g_strfreev(lines); g_strfreev(lines);
g_string_erase(in->buf, 0, p - in->buf->str); g_string_erase(in->buf, 0, processed_up_to - in->buf->str);
return ret; return ret;
} }