extexi

GNU的词法/语法分析器bison源码

# Extract all examples from the manual source.            -*- AWK -*-

# This file is part of GNU Bison
# Copyright 1992, 2000, 2001, 2005 Free Software Foundation, Inc.
#
# This program is free software; you can redistribute it and/or modify
# it under the terms of the GNU General Public License as published by
# the Free Software Foundation; either version 2 of the License, or
# (at your option) any later version.
#
# This program is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
# GNU General Public License for more details.
#
# You should have received a copy of the GNU General Public License
# along with this program; if not, write to the Free Software
# Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA
# 02111-1307  USA

# This script is for use with any Awk that conforms to POSIX.
# It was derived from a similar script tests/generate.awk in GNU m4.
#
# Usage: extexi input-file.texi ... -- [FILES to extract]
BEGIN {
  if (!output_dir)
    output_dir = ".";
  for (argc = 1; argc < ARGC; ++argc)
    if (ARGV[argc] == "--")
      break;
  for (i = argc + 1; i < ARGC; ++i)
    file_wanted[ARGV[i]] = 1;
  ARGC = argc;
}

/^@node / {
  if (seq > 0)
    print "AT_CLEANUP";

  split ($0, tmp, ",");
  node = substr(tmp[1], 7);
  seq = 0;
}

/^@comment file: / {
  if (!file_wanted[$3])
    message("ignoring " $3);
  else
    {
      message("extracting " $3);
      file = $3;
    }
}

/^@example$/, /^@end example$/ {
  if (!file)
    next;

  if ($0 ~ /^@example$/)
    {
      input = files_output[file] ? "\n" : "";

      # FNR is starting at 0 instead of 1, and
      # #line report the line number of the *next* line.
      # => + 2.
      # Note that recent Bison support it, but not Flex.
      if (file ~ /\.[chy]*$/)
	input = "#line " (FNR + 1) " \"" FILENAME "\"\n";
      next;
    }

  if ($0 ~ /^@end example$/)
    {
      if (input == "")
	fatal("no contents: " file);

      input = normalize(input);
      # No spurious end of line: use printf.
      if (files_output[file])
	printf ("%s", input) >> output_dir "/" file;
      else
	printf ("%s", input) > output_dir "/" file;
      close (output_dir "/" file);
      files_output[file] = 1;

      file = input = "";
      next;
    }

  input = input $0 "\n";
}


# We have to handle CONTENTS line per line, since anchors in AWK are
# referring to the whole string, not the lines.
function normalize(contents,    i, lines, n, line, res) {
  # Remove the Texinfo tags.
  n = split (contents, lines, "\n");
  # We don't want the last field which empty: it's behind the last \n.
  for (i = 1; i < n; ++i)
    {
      line = lines[i];

      # Whole line commands.
      if (line ~ /^@(c |comment|dots|end (ignore|group)|ignore|group)/)
	# Gperf accepts empty lines as valid input!!!
	if (file ~ /\.gperf$/)
	  continue;
	else
	  line = "";

      gsub (/^@result\{\}/, "", line);
      gsub (/^@error\{\}/,  "", line);
      gsub ("@[{]", "{", line);
      gsub ("@}", "}", line);
      gsub ("@@", "@", line);
      gsub ("@comment.*", "", line);

      res = res line "\n";
    }
  return res;
}


function message(msg) {
  if (! message_printed[msg])
    {
      print "extexi: " msg > "/dev/stderr";
      message_printed[msg] = 1;
    }
}

function fatal(msg) {
  message(msg);
  exit 1
}