Hi Thomas,
On Fri, 5 Jul 2019, Thomas Gummerer wrote:
> Currently range-diff uses the 'strbuf_getline()' function for doing
> its line by line processing. In a future patch we want to do parts of
> that parsing using the 'parse_git_header()' function, which does
If you like my suggestion in patch 7/14, this commit message needs to talk
about the new name, too.
> requires reading parts of the input from that function, which doesn't
s/requires/require/
> use strbufs.
>
> Switch range-diff to do our own line by line parsing, so we can re-use
> the parse_git_header function later.
>
> Signed-off-by: Thomas Gummerer <t.gummerer@xxxxxxxxx>
> ---
>
> Longer term it might be better to have both range-diff and apply code
> use strbufs. However I didn't feel it's worth making that change for
> this patch series.
Makes sense.
> range-diff.c | 69 +++++++++++++++++++++++++++++-----------------------
> 1 file changed, 39 insertions(+), 30 deletions(-)
>
> diff --git a/range-diff.c b/range-diff.c
> index 9242b8975f..916afa44c0 100644
> --- a/range-diff.c
> +++ b/range-diff.c
> @@ -24,6 +24,17 @@ struct patch_util {
> struct object_id oid;
> };
>
> +static unsigned long linelen(const char *buffer, unsigned long size)
Shouldn't this be `size_t`?
> +{
> + unsigned long len = 0;
Likewise.
> + while (size--) {
> + len++;
> + if (*buffer++ == '\n')
> + break;
> + }
> + return len;
How about
const char *eol = memchr(buffer, '\n', size);
return !eol ? size : eol + 1 - buffer;
instead?
For an extra brownie point, you could even rename this function to
`find_end_of_line()` and replace the LF by a NUL:
if (!eol)
return size;
*eol = '\0';
return eol + 1 - buffer;
> +}
> +
> /*
> * Reads the patches into a string list, with the `util` field being populated
> * as struct object_id (will need to be free()d).
> @@ -31,10 +42,12 @@ struct patch_util {
> static int read_patches(const char *range, struct string_list *list)
> {
> struct child_process cp = CHILD_PROCESS_INIT;
> - FILE *in;
> - struct strbuf buf = STRBUF_INIT, line = STRBUF_INIT;
> + struct strbuf buf = STRBUF_INIT, file = STRBUF_INIT;
This puzzled me. I'd like to suggest s/file/contents/
> struct patch_util *util = NULL;
> int in_header = 1;
> + char *line;
> + int offset, len;
> + size_t size;
>
> argv_array_pushl(&cp.args, "log", "--no-color", "-p", "--no-merges",
> "--reverse", "--date-order", "--decorate=no",
> @@ -54,17 +67,15 @@ static int read_patches(const char *range, struct string_list *list)
>
> if (start_command(&cp))
> return error_errno(_("could not start `log`"));
> - in = fdopen(cp.out, "r");
> - if (!in) {
> - error_errno(_("could not read `log` output"));
> - finish_command(&cp);
> - return -1;
> - }
> + strbuf_read(&file, cp.out, 0);
Shouldn't we handle a negative return value here, erroring out with "could
not read `log` output" as before?
>
> - while (strbuf_getline(&line, in) != EOF) {
> + line = strbuf_detach(&file, &size);
I strongly suspect this to leak, given that `line` is subsequently
advanced, and there is no backup copy.
Maybe
line = file.buf;
size = file.len;
would make more sense here?
> + for (offset = 0; size > 0; offset += len, size -= len, line += len) {
> const char *p;
>
> - if (skip_prefix(line.buf, "commit ", &p)) {
> + len = linelen(line, size);
> + line[len - 1] = '\0';
> + if (skip_prefix(line, "commit ", &p)) {
> if (util) {
> string_list_append(list, buf.buf)->util = util;
> strbuf_reset(&buf);
> @@ -75,8 +86,6 @@ static int read_patches(const char *range, struct string_list *list)
> free(util);
> string_list_clear(list, 1);
> strbuf_release(&buf);
> - strbuf_release(&line);
> - fclose(in);
We should release the file contents in `file` (or `contents`, if you like
my suggestions) here.
> finish_command(&cp);
> return -1;
> }
> @@ -85,26 +94,28 @@ static int read_patches(const char *range, struct string_list *list)
> continue;
> }
>
> - if (starts_with(line.buf, "diff --git")) {
> + if (starts_with(line, "diff --git")) {
> in_header = 0;
> strbuf_addch(&buf, '\n');
> if (!util->diff_offset)
> util->diff_offset = buf.len;
> strbuf_addch(&buf, ' ');
> - strbuf_addbuf(&buf, &line);
> + strbuf_addstr(&buf, line);
> } else if (in_header) {
> - if (starts_with(line.buf, "Author: ")) {
> - strbuf_addbuf(&buf, &line);
> + if (starts_with(line, "Author: ")) {
> + strbuf_addstr(&buf, line);
> strbuf_addstr(&buf, "\n\n");
> - } else if (starts_with(line.buf, " ")) {
> - strbuf_rtrim(&line);
> - strbuf_addbuf(&buf, &line);
> + } else if (starts_with(line, " ")) {
> + p = line + len - 2;
> + while (isspace(*p) && p >= line)
> + p--;
> + strbuf_add(&buf, line, p - line + 1);
> strbuf_addch(&buf, '\n');
> }
> continue;
> - } else if (starts_with(line.buf, "@@ "))
> + } else if (starts_with(line, "@@ "))
> strbuf_addstr(&buf, "@@");
> - else if (!line.buf[0] || starts_with(line.buf, "index "))
> + else if (!line[0] || starts_with(line, "index "))
> /*
> * A completely blank (not ' \n', which is context)
> * line is not valid in a diff. We skip it
> @@ -117,25 +128,23 @@ static int read_patches(const char *range, struct string_list *list)
> * we are not interested.
> */
> continue;
> - else if (line.buf[0] == '>') {
> + else if (line[0] == '>') {
> strbuf_addch(&buf, '+');
> - strbuf_add(&buf, line.buf + 1, line.len - 1);
> - } else if (line.buf[0] == '<') {
> + strbuf_addstr(&buf, line + 1);
> + } else if (line[0] == '<') {
> strbuf_addch(&buf, '-');
> - strbuf_add(&buf, line.buf + 1, line.len - 1);
> - } else if (line.buf[0] == '#') {
> + strbuf_addstr(&buf, line + 1);
> + } else if (line[0] == '#') {
> strbuf_addch(&buf, ' ');
> - strbuf_add(&buf, line.buf + 1, line.len - 1);
> + strbuf_addstr(&buf, line + 1);
> } else {
> strbuf_addch(&buf, ' ');
> - strbuf_addbuf(&buf, &line);
> + strbuf_addstr(&buf, line);
> }
>
> strbuf_addch(&buf, '\n');
> util->diffsize++;
> }
> - fclose(in);
> - strbuf_release(&line);
We should release the file contents we previously read via `strbuf_read()` here.
Ciao,
Dscho
>
> if (util)
> string_list_append(list, buf.buf)->util = util;
> --
> 2.22.0.510.g264f2c817a
>
>
