grep: -T now adjusts number widths for worst case

* NEWS, doc/grep.texi (Output Line Prefix Control):
Document this (Bug#24451).
* src/grep.c (offset_width): New static var.
(print_offset): Use it instead of arg.  All callers changed.
(grep): Set it.
* tests/initial-tab: Test this.

4 files changed, 32 insertions, 11 deletions

diff --git a/NEWS b/NEWS
index 0037edd7..978ec555 100644
--- a/NEWS
+++ b/NEWS
@@ -20,6 +20,10 @@ GNU grep NEWS                                    -*- outline -*-
   longer outputs tab-backspace-':'-C, an approach that has problems if
   run inside an Emacs shell window.  [bug introduced in grep-2.5.2]
 
+  grep -T now uses worst-case widths of line numbers and byte offsets
+  instead of guessing widths that might not work with larger files.
+  [bug introduced in grep-2.5.2]
+
   grep's use of getprogname no longer causes a build failure on HP-UX.
 
 ** Improvements
diff --git a/doc/grep.texi b/doc/grep.texi
index 9af13c42..3a12dce2 100644
--- a/doc/grep.texi
+++ b/doc/grep.texi
@@ -463,10 +463,8 @@ Make sure that the first character of actual line content lies on a tab stop,
 so that the alignment of tabs looks normal.
 This is useful with options that prefix their output to the actual content:
 @option{-H}, @option{-n}, and @option{-b}.
-In order to improve the probability that lines
-from a single file will all start at the same column,
-this also causes the line number and byte offset (if present)
-to be printed in a minimum-size field width.
+This may also prepend spaces to output line numbers and byte offsets
+so that lines from a single file all start at the same column.
 
 @item -u
 @itemx --unix-byte-offsets
diff --git a/src/grep.c b/src/grep.c
index 86cf18b9..62866cbd 100644
--- a/src/grep.c
+++ b/src/grep.c
@@ -81,6 +81,9 @@ static bool only_matching;
 /* If nonzero, make sure first content char in a line is on a tab stop. */
 static bool align_tabs;
 
+/* Print width of line numbers and byte offsets.  Nonzero if ALIGN_TABS.  */
+static int offset_width;
+
 /* See below */
 struct FL_pair
   {
@@ -1079,12 +1082,13 @@ print_sep (char sep)
 
 /* Print a line number or a byte offset.  */
 static void
-print_offset (uintmax_t pos, int min_width, const char *color)
+print_offset (uintmax_t pos, const char *color)
 {
 #if !HAVE_PRINTF_C99_SIZES
   /* Do not rely on printf to print pos, since uintmax_t may be longer
      than long, and long long is not portable.  */
 
+  int min_width = offset_width;
   char buf[sizeof pos * CHAR_BIT];
   char *p = buf + sizeof buf;
 
@@ -1096,14 +1100,13 @@ print_offset (uintmax_t pos, int min_width, const char *color)
   while ((pos /= 10) != 0);
 
   /* Do this to maximize the probability of alignment across lines.  */
-  if (align_tabs)
-    while (--min_width >= 0)
-      *--p = ' ';
+  while (--min_width >= 0)
+    *--p = ' ';
 #endif /* !HAVE_PRINTF_C99_SIZES */
 
   pr_sgr_start_if (color);
 #if HAVE_PRINTF_C99_SIZES
-  printf_errno ("%*ju", align_tabs ? min_width : 0, pos);
+  printf_errno ("%*ju", offset_width, pos);
 #else
   fwrite_errno (p, 1, buf + sizeof buf - p);
 #endif
@@ -1151,7 +1154,7 @@ print_line_head (char *beg, size_t len, char const *lim, char sep)
           totalnl = add_count (totalnl, 1);
           lastnl = lim;
         }
-      print_offset (totalnl, 4, line_num_color);
+      print_offset (totalnl, line_num_color);
       print_sep (sep);
     }
 
@@ -1159,7 +1162,7 @@ print_line_head (char *beg, size_t len, char const *lim, char sep)
     {
       uintmax_t pos = add_count (totalcc, beg - bufbeg);
       pos = dossified_pos (pos);
-      print_offset (pos, 6, byte_num_color);
+      print_offset (pos, byte_num_color);
       print_sep (sep);
     }
 
@@ -1511,6 +1514,17 @@ grep (int fd, struct stat const *st, bool *ineof)
       return 0;
     }
 
+  offset_width = 0;
+  if (align_tabs)
+    {
+      /* Width is log of maximum number.  Line numbers are origin-1.  */
+      uintmax_t num = usable_st_size (st) ? st->st_size : UINTMAX_MAX;
+      num += out_line && num < UINTMAX_MAX;
+      do
+        offset_width++;
+      while ((num /= 10) != 0);
+    }
+
   for (bool firsttime = true; ; firsttime = false)
     {
       if (nlines_first_null < 0 && eol && binary_files != TEXT_BINARY_FILES
diff --git a/tests/initial-tab b/tests/initial-tab
index af5efb37..8b3cb8c4 100755
--- a/tests/initial-tab
+++ b/tests/initial-tab
@@ -29,4 +29,9 @@ printf 'in:\tx\nin:\n' > exp || framework_failure_
 grep -T '^' in /dev/null > out || fail=1
 compare exp out || fail=1
 
+printf '%s\n' a b c d e f g h i j > in1 || framework_failure_
+printf 'in1: 1:\ta\n' > exp1 || framework_failure_
+grep -Tn 'a' in1 /dev/null > out1 || fail=1
+compare exp1 out1 || fail=1
+
 Exit $fail