Hi Pádraig, Finally, I found time to work again on this patch. I provided it as attachment.
I'm not completely satisfied with the documentation part. I've tried to be more specific but it becomes quickly complicated. So I get back the original explanation which does not completely satisfied me since it does not explain the following point: - When -a is not specified: - output file names are considered exhausted when the first suffix character will become 'z'. -'z[a-z]' suffixes are never used - the fact that suffix length is increased each time the suffix are "exhausted". But maybe it's not relevant to be so specific. What is your opinion about this point ? > Good. That's what I'd prefer anyway so as to be compatible with old > data sets. Note '.' sorts before digits (-d) too, so there should be > no ordering issues with --additional-suffix=... either. In fact, it depends on the current locale. With my locale, "." is not sorted this way. Cheers, Jérémy
From 9060e4b80a8b038b2de7f68e07f306f8d98f18d5 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?J=C3=A9r=C3=A9my=20Compostella?= <[email protected]> Date: Thu, 1 Mar 2012 20:37:41 +0100 Subject: [PATCH] split: add unlimited split files as default behavior * src/split.c (next_file_name): If `suffix_auto' is true and the first suffix character is 'z', generate a new file file name adding `z' to the prefix and increasing the suffix length by one. (main): If `-a' is specified, disable unlimited split files feature. * doc/coreutils.texi (split invocation): Mention it. * NEWS (Improvements): Mention it. --- NEWS | 2 ++ doc/coreutils.texi | 8 +++++--- src/split.c | 41 +++++++++++++++++++++++++++++++++++++---- 3 files changed, 44 insertions(+), 7 deletions(-) diff --git a/NEWS b/NEWS index 8006669..e0f5d6c 100644 --- a/NEWS +++ b/NEWS @@ -37,6 +37,8 @@ GNU coreutils NEWS -*- outline -*- systems for which getfilecon-, ACL-check- and XATTR-check-induced syscalls fail with ENOTSUP or similar. + split now supports unlimited number of split files as default behavior. + * Noteworthy changes in release 8.15 (2012-01-06) [stable] diff --git a/doc/coreutils.texi b/doc/coreutils.texi index 4a4cadb..2ab61a4 100644 --- a/doc/coreutils.texi +++ b/doc/coreutils.texi @@ -2990,9 +2990,11 @@ The output files' names consist of @var{prefix} (@samp{x} by default) followed by a group of characters (@samp{aa}, @samp{ab}, @dots{} by default), such that concatenating the output files in traditional sorted order by file name produces the original input file (except -@option{-nr/@var{n}}). If the output file names are exhausted, -@command{split} reports an error without deleting the output files -that it did create. +@option{-nr/@var{n}}). If more than 676 output files are required and +@samp{-a} is not specified, @command{split} uses @samp{zaaa}, +@samp{zaab}, etc. If the @option{-a} is specified and the output file +names are exhausted, @command{split} reports an error without deleting +the output files that it did create. The program accepts the following options. Also see @ref{Common options}. diff --git a/src/split.c b/src/split.c index 68c9a34..34ba092 100644 --- a/src/split.c +++ b/src/split.c @@ -74,6 +74,9 @@ static char *outfile; Suffixes are inserted here. */ static char *outfile_mid; +/* Generate new suffix when suffixes are exhausted. */ +static bool suffix_auto = true; + /* Length of OUTFILE's suffix. */ static size_t suffix_length; @@ -242,14 +245,18 @@ next_file_name (void) { /* Index in suffix_alphabet of each character in the suffix. */ static size_t *sufindex; + static size_t outbase_length; + static size_t outfile_length; + static size_t addsuf_length; if (! outfile) { /* Allocate and initialize the first file name. */ - size_t outbase_length = strlen (outbase); - size_t addsuf_length = additional_suffix ? strlen (additional_suffix) : 0; - size_t outfile_length = outbase_length + suffix_length + addsuf_length; + outbase_length = strlen (outbase); + addsuf_length = additional_suffix ? strlen (additional_suffix) : 0; + outfile_length = outbase_length + suffix_length + addsuf_length; + if (outfile_length + 1 < outbase_length) xalloc_die (); outfile = xmalloc (outfile_length + 1); @@ -295,13 +302,38 @@ next_file_name (void) while (i-- != 0) { sufindex[i]++; + if (suffix_auto && i == 0 && !suffix_alphabet[sufindex[i] + 1]) + break; outfile_mid[i] = suffix_alphabet[sufindex[i]]; if (outfile_mid[i]) return; sufindex[i] = 0; outfile_mid[i] = suffix_alphabet[sufindex[i]]; } - error (EXIT_FAILURE, 0, _("output file suffixes exhausted")); + + if (!suffix_auto) + error (EXIT_FAILURE, 0, _("output file suffixes exhausted")); + + /* Otherwise, initialize a new first file name. */ + + outfile_length += 2; + outfile = xrealloc (outfile, outfile_length + 1); + outfile[outfile_length] = 0; + + /* Append the last alphabet character to the file name + prefix. */ + outfile[outbase_length] = suffix_alphabet[sufindex[i]]; + outbase_length++; + outfile_mid = outfile + outbase_length; + + /* Extend the suffix length by one. */ + suffix_length++; + sufindex = xrealloc (sufindex, suffix_length * sizeof *sufindex); + memset (sufindex, 0, suffix_length * sizeof *sufindex); + memset (outfile_mid, suffix_alphabet[0], suffix_length); + + if (additional_suffix) + memcpy (outfile_mid + suffix_length, additional_suffix, addsuf_length); } } @@ -1059,6 +1091,7 @@ main (int argc, char **argv) usage (EXIT_FAILURE); } suffix_length = tmp; + suffix_auto = false; } break; -- 1.7.2.5
