diff options
Diffstat (limited to 'doc/gawk.texi')
| -rw-r--r-- | doc/gawk.texi | 68 |
1 files changed, 36 insertions, 32 deletions
diff --git a/doc/gawk.texi b/doc/gawk.texi index aef39200..fb982a09 100644 --- a/doc/gawk.texi +++ b/doc/gawk.texi @@ -8521,31 +8521,24 @@ input record and split it up into fields. This is useful if you've finished processing the current record, but want to do some special processing on the next record @emph{right now}. For example: +@c 6/2019: Thanks to Mark Krauze <daburashka@ya.ru> for suggested +@c improvements (the inner while loop). @example # Remove text between /* and */, inclusive @{ - if ((i = index($0, "/*")) != 0) @{ - out = substr($0, 1, i - 1) # leading part of the string - rest = substr($0, i + 2) # ... */ ... - j = index(rest, "*/") # is */ in trailing part? - if (j > 0) @{ - rest = substr(rest, j + 2) # remove comment - @} else @{ - while (j == 0) @{ - # get more text - if (getline <= 0) @{ - print("unexpected EOF or error:", ERRNO) > "/dev/stderr" - exit - @} - # build up the line using string concatenation - rest = rest $0 - j = index(rest, "*/") # is */ in trailing part? - if (j != 0) @{ - rest = substr(rest, j + 2) - break - @} + while ((start = index($0, "/*")) != 0) @{ + out = substr($0, 1, start - 1) # leading part of the string + rest = substr($0, start + 2) # ... */ ... + while ((end = index(rest, "*/")) == 0) @{ # is */ in trailing part? + # get more text + if (getline <= 0) @{ + print("unexpected EOF or error:", ERRNO) > "/dev/stderr" + exit @} + # build up the line using string concatenation + rest = rest $0 @} + rest = substr(rest, end + 2) # remove comment # build up the output line using string concatenation $0 = out rest @} @@ -8553,16 +8546,6 @@ processing on the next record @emph{right now}. For example: @} @end example -@c 8/2014: Here is some sample input: -@ignore -mon/*comment*/key -rab/*commen -t*/bit -horse /*comment*/more text -part 1 /*comment*/part 2 /*comment*/part 3 -no comment -@end ignore - This @command{awk} program deletes C-style comments (@samp{/* @dots{} */}) from the input. It uses a number of features we haven't covered yet, including @@ -8574,8 +8557,29 @@ functions By replacing the @samp{print $0} with other statements, you could perform more complicated processing on the decommented input, such as searching for matches of a regular -expression. (This program has a subtle problem---it does not work if one -comment ends and another begins on the same line.) +expression. + +Here is some sample input: + +@example +mon/*comment*/key +rab/*commen +t*/bit +horse /*comment*/more text +part 1 /*comment*/part 2 /*comment*/part 3 +no comment +@end example + +When run, the output is: + +@example +$ @kbd{awk -f strip_comments.awk example_text} +@print{} monkey +@print{} rabbit +@print{} horse more text +@print{} part 1 part 2 part 3 +@print{} no comment +@end example This form of the @code{getline} command sets @code{NF}, @code{NR}, @code{FNR}, @code{RT}, and the value of @code{$0}. |