gitlog-to-changelog: provide a ChangeLog-repair mechanism

Git logs are often treated as immutable, because editing them
changes the SHA1 checksums of all descendants.  Thus, errors in
git logs tend to stay there forever.  However, when we generate
a ChangeLog file -- typically for distribution -- from that git log,
we can actually make corrections in the generated file.  The key
lies in recording in machine-readable/applicable form the desired
corrections.  See --help for description and an example.
* build-aux/gitlog-to-changelog (parse_amend_file): New function.
(usage): Describe it; alphabetize option descriptions.
(main): Honor the new option, carefully.

diff --git a/ChangeLog b/ChangeLog
index 1fece4d..2218b2e 100644 (file)
--- a/ChangeLog
+++ b/ChangeLog
@@ -1,3 +1,17 @@
+2011-11-02  Jim Meyering  <meyering@redhat.com>
+
+       gitlog-to-changelog: provide a ChangeLog-repair mechanism
+       Git logs are often treated as immutable, because editing them
+       changes the SHA1 checksums of all descendants.  Thus, errors in
+       git logs tend to stay there forever.  However, when we generate
+       a ChangeLog file -- typically for distribution -- from that git log,
+       we can actually make corrections in the generated file.  The key
+       lies in recording in machine-readable/applicable form the desired
+       corrections.  See --help for description and an example.
+       * build-aux/gitlog-to-changelog (parse_amend_file): New function.
+       (usage): Describe it; alphabetize option descriptions.
+       (main): Honor the new option, carefully.
+
 2011-11-01  Jim Meyering  <meyering@redhat.com>
 
        gitlog-to-changelog: avoid an infloop

diff --git a/build-aux/gitlog-to-changelog b/build-aux/gitlog-to-changelog
index 4612d38..56c7e4e 100755 (executable)
--- a/build-aux/gitlog-to-changelog
+++ b/build-aux/gitlog-to-changelog
@@ -3,7 +3,7 @@ eval '(exit $?0)' && eval 'exec perl -wS "$0" ${1+"$@"}'
     if 0;
 # Convert git log output to ChangeLog format.
 
-my $VERSION = '2011-10-31 16:06'; # UTC
+my $VERSION = '2011-11-02 07:53'; # UTC
 # The definition above must lie within the first 8 lines in order
 # for the Emacs time-stamp write hook (at end) to update it.
 # If you change this file with Emacs, please let the write hook
@@ -60,13 +60,15 @@ $ME, they may be preceded by '--'.
 
 OPTIONS:
 
+   --amend=FILE FILE maps from an SHA1 to perl code (i.e., s/old/new/) that
+                  makes a change to SHA1's commit log text or metadata.
+   --append-dot append a dot to the first line of each commit message if
+                  there is no other punctuation or blank at the end.
    --since=DATE convert only the logs since DATE;
                   the default is to convert all log entries.
    --format=FMT set format string for commit subject and body;
                   see 'man git-log' for the list of format metacharacters;
                   the default is '%s%n%b%n'
-   --append-dot append a dot to the first line of each commit message if
-                  there is no other punctuation or blank at the end.
 
    --help       display this help and exit
    --version    output version information and exit
@@ -76,6 +78,23 @@ EXAMPLE:
   $ME --since=2008-01-01 > ChangeLog
   $ME -- -n 5 foo > last-5-commits-to-branch-foo
 
+In a FILE specified via --amend, comment lines (starting with "#") are ignored.
+FILE must consist of <SHA,CODE+> pairs where SHA is a 40-byte SHA1 (alone on
+a line) referring to a commit in the current project, and CODE refers to one
+or more consecutive lines of Perl code.  Pairs must be separated by one or
+more blank line.
+
+Here is sample input for use with --amend=FILE, from coreutils:
+
+3a169f4c5d9159283548178668d2fae6fced3030
+# fix typo in title:
+s/all tile types/all file types/
+
+1379ed974f1fa39b12e2ffab18b3f7a607082202
+# Due to a bug in vc-dwim, I mis-attributed a patch by Paul to myself.
+# Change the author to be Paul.  Note the escaped "@":
+s,Jim .*>,Paul Eggert <eggert\@cs.ucla.edu>,
+
 EOF
     }
   exit $exit_code;
@@ -101,9 +120,60 @@ sub quoted_cmd(@)
   return join (' ', map {shell_quote $_} @_);
 }
 
+# Parse file F.
+# Comment lines (starting with "#") are ignored.
+# F must consist of <SHA,CODE+> pairs where SHA is a 40-byte SHA1
+# (alone on a line) referring to a commit in the current project, and
+# CODE refers to one or more consecutive lines of Perl code.
+# Pairs must be separated by one or more blank line.
+sub parse_amend_file($)
+{
+  my ($f) = @_;
+
+  open F, '<', $f
+    or die "$ME: $f: failed to open for reading: $!\n";
+
+  my $fail;
+  my $h = {};
+  my $in_code = 0;
+  my $sha;
+  while (defined (my $line = <F>))
+    {
+      $line =~ /^\#/
+        and next;
+      chomp $line;
+      $line eq ''
+        and $in_code = 0, next;
+
+      if (!$in_code)
+        {
+          $line =~ /^([0-9a-fA-F]{40})$/
+            or (warn "$ME: $f:$.: invalid line; expected an SHA1\n"),
+              $fail = 1, next;
+          $sha = lc $1;
+          $in_code = 1;
+          exists $h->{$sha}
+            and (warn "$ME: $f:$.: duplicate SHA1\n"),
+              $fail = 1, next;
+        }
+      else
+        {
+          $h->{$sha} ||= '';
+          $h->{$sha} .= "$line\n";
+        }
+    }
+  close F;
+
+  $fail
+    and exit 1;
+
+  return $h;
+}
+
 {
   my $since_date;
   my $format_string = '%s%n%b%n';
+  my $amend_file;
   my $append_dot = 0;
   GetOptions
     (
@@ -111,14 +181,20 @@ sub quoted_cmd(@)
      version => sub { print "$ME version $VERSION\n"; exit },
      'since=s' => \$since_date,
      'format=s' => \$format_string,
+     'amend=s' => \$amend_file,
      'append-dot' => \$append_dot,
     ) or usage 1;
 
+
   defined $since_date
     and unshift @ARGV, "--since=$since_date";
 
+  # This is a hash that maps an SHA1 to perl code (i.e., s/old/new/)
+  # that makes a correction in the log or attribution of that commit.
+  my $amend_code = defined $amend_file ? parse_amend_file $amend_file : {};
+
   my @cmd = (qw (git log --log-size),
-             '--pretty=format:%ct  %an  <%ae>%n%n'.$format_string, @ARGV);
+             '--pretty=format:%H:%ct  %an  <%ae>%n%n'.$format_string, @ARGV);
   open PIPE, '-|', @cmd
     or die ("$ME: failed to run `". quoted_cmd (@cmd) ."': $!\n"
             . "(Is your Git too old?  Version 1.5.1 or later is required.)\n");
@@ -137,7 +213,34 @@ sub quoted_cmd(@)
       $n_read == $log_nbytes
         or die "$ME:$.: unexpected EOF\n";
 
-      my @line = split "\n", $log;
+      # Extract leading hash.
+      my ($sha, $rest) = split ':', $log, 2;
+      defined $sha
+        or die "$ME:$.: malformed log entry\n";
+      $sha =~ /^[0-9a-fA-F]{40}$/
+        or die "$ME:$.: invalid SHA1: $sha\n";
+
+      # If this commit's log requires any transformation, do it now.
+      my $code = $amend_code->{$sha};
+      if (defined $code)
+        {
+          eval 'use Safe';
+          my $s = new Safe;
+          # Put the unpreprocessed entry into "$_".
+          $_ = $rest;
+
+          # Let $code operate on it, safely.
+          my $r = $s->reval("$code")
+            or die "$ME:$.:$sha: failed to eval \"$code\":\n$@\n";
+
+          # Note that we've used this entry.
+          delete $amend_code->{$sha};
+
+          # Update $rest upon success.
+          $rest = $_;
+        }
+
+      my @line = split "\n", $rest;
       my $author_line = shift @line;
       defined $author_line
         or die "$ME:$.: unexpected EOF\n";
@@ -200,6 +303,16 @@ sub quoted_cmd(@)
   close PIPE
     or die "$ME: error closing pipe from " . quoted_cmd (@cmd) . "\n";
   # FIXME-someday: include $PROCESS_STATUS in the diagnostic
+
+  # Complain about any unused entry in the --amend=F specified file.
+  my $fail = 0;
+  foreach my $sha (keys %$amend_code)
+    {
+      warn "$ME:$amend_file: unused entry: $sha\n";
+      $fail = 1;
+    }
+
+  exit $fail;
 }
 
 # Local Variables: