It occurred to me -- and I know it will sound like a heresy -- that
maybe providing an overly long example in C is not the best option here.
Why not page_owner.py with the following content instead (not tested):
#!/usr/bin/python
import collections
import sys
counts = collections.defaultdict(int)
txt = ''
for line in sys.stdin:
if line == '\n':
counts[txt] += 1
txt = ''
else:
txt += line
counts[txt] += 1
for txt, num in sorted(counts.items(), txt=lambda x: x[1]):
if len(txt) > 1:
print '%d times:\n%s' % num, txt
And it's so “long” only because I chose not to read the whole file at
once as in:
counts = collections.defaultdict(int)
for txt in sys.stdin.read().split('\n\n'):
counts[txt] += 1
On Fri, Jan 11 2013, Minchan Kim wrote:
> The read_block reads char one by one until meeting two newline.
> It's not good for the performance and current code isn't good shape
> for readability.
>
> This patch enhances speed and clean up.
>
> Cc: Mel Gorman <mgorman@xxxxxxx>
> Cc: Andy Whitcroft <apw@xxxxxxxxxxxx>
> Cc: Alexander Nyberg <alexn@xxxxxxxxx>
> Cc: Randy Dunlap <rdunlap@xxxxxxxxxxxxx>
> Signed-off-by: Michal Nazarewicz <mina86@xxxxxxxxxx>
> Signed-off-by: Minchan Kim <minchan@xxxxxxxxxx>
> ---
> Documentation/page_owner.c | 34 +++++++++++++---------------------
> 1 file changed, 13 insertions(+), 21 deletions(-)
>
> diff --git a/Documentation/page_owner.c b/Documentation/page_owner.c
> index 43dde96..96bf481 100644
> --- a/Documentation/page_owner.c
> +++ b/Documentation/page_owner.c
> @@ -28,26 +28,17 @@ static int max_size;
>
> struct block_list *block_head;
>
> -int read_block(char *buf, FILE *fin)
> +int read_block(char *buf, int buf_size, FILE *fin)
> {
> - int ret = 0;
> - int hit = 0;
> - int val;
> - char *curr = buf;
> -
> - for (;;) {
> - val = getc(fin);
> - if (val == EOF) return -1;
> - *curr = val;
> - ret++;
> - if (*curr == '\n' && hit == 1)
> - return ret - 1;
> - else if (*curr == '\n')
> - hit = 1;
> - else
> - hit = 0;
> - curr++;
> + char *curr = buf, *const buf_end = buf + buf_size;
> +
> + while (buf_end - curr > 1 && fgets(curr, buf_end - curr, fin)) {
> + if (*curr == '\n') /* empty line */
> + return curr - buf;
> + curr += strlen(curr);
> }
> +
> + return -1; /* EOF or no space left in buf. */
> }
>
> static int compare_txt(struct block_list *l1, struct block_list *l2)
> @@ -84,10 +75,12 @@ static void add_list(char *buf, int len)
> }
> }
>
> +#define BUF_SIZE 1024
> +
> int main(int argc, char **argv)
> {
> FILE *fin, *fout;
> - char buf[1024];
> + char buf[BUF_SIZE];
> int ret, i, count;
> struct block_list *list2;
> struct stat st;
> @@ -106,11 +99,10 @@ int main(int argc, char **argv)
> list = malloc(max_size * sizeof(*list));
>
> for(;;) {
> - ret = read_block(buf, fin);
> + ret = read_block(buf, BUF_SIZE, fin);
> if (ret < 0)
> break;
>
> - buf[ret] = '\0';
> add_list(buf, ret);
> }
>
> --
> 1.7.9.5
>
--
Best regards, _ _
.o. | Liege of Serenely Enlightened Majesty of o' \,=./ `o
..o | Computer Science, Michał “mina86” Nazarewicz (o o)
ooo +----<email/xmpp: mpn@xxxxxxxxxx>--------------ooO--(_)--Ooo--Attachment:
pgpaT88Gm9fZR.pgp
Description: PGP signature