dictfmt 1.12.1+dfsg-3 / usr / bin / dictunformat

#!/bin/sh

#
# Writen by Aleksey Cheusov
# Public Domain
#

LC_ALL=C
export LC_ALL

exec awk '
BEGIN {
	NL_size   = 1 # 2 for \r\n
	separator = ";   "
	SUBSEP    = "\t"
}

function usage (){
	printf "%s", "\
dictunformat takes a dictionary index file\n\
 as the parameter and a dictionary database file\n\
 on stdin and outputs text which may be used\n\
 to create DICT database by \"dictfmt -t\"\n\
\n\
usage: dictunformat [OPTIONS] <index_filename>\n\
  OPTIONS:\n\
    --help                       display this screen\n\
    --headword-separator <sep>   set headword separator.\n\
                                 the default is `;   `\n\
    --index-data-separator <sep> set index/data separator.\n\
                                 the default is `\\034`\n\
"
}

BEGIN {
	b64_index ["+"] = 62
	b64_index ["/"] = 63
	b64_index ["0"] = 52
	b64_index ["1"] = 53
	b64_index ["2"] = 54
	b64_index ["3"] = 55
	b64_index ["4"] = 56
	b64_index ["5"] = 57
	b64_index ["6"] = 58
	b64_index ["7"] = 59
	b64_index ["8"] = 60
	b64_index ["9"] = 61
	b64_index ["A"] = 0
	b64_index ["B"] = 1
	b64_index ["C"] = 2
	b64_index ["D"] = 3
	b64_index ["E"] = 4
	b64_index ["F"] = 5
	b64_index ["G"] = 6
	b64_index ["H"] = 7
	b64_index ["I"] = 8
	b64_index ["J"] = 9
	b64_index ["K"] = 10
	b64_index ["L"] = 11
	b64_index ["M"] = 12
	b64_index ["N"] = 13
	b64_index ["O"] = 14
	b64_index ["P"] = 15
	b64_index ["Q"] = 16
	b64_index ["R"] = 17
	b64_index ["S"] = 18
	b64_index ["T"] = 19
	b64_index ["U"] = 20
	b64_index ["V"] = 21
	b64_index ["W"] = 22
	b64_index ["X"] = 23
	b64_index ["Y"] = 24
	b64_index ["Z"] = 25
	b64_index ["a"] = 26
	b64_index ["b"] = 27
	b64_index ["c"] = 28
	b64_index ["d"] = 29
	b64_index ["e"] = 30
	b64_index ["f"] = 31
	b64_index ["g"] = 32
	b64_index ["h"] = 33
	b64_index ["i"] = 34
	b64_index ["j"] = 35
	b64_index ["k"] = 36
	b64_index ["l"] = 37
	b64_index ["m"] = 38
	b64_index ["n"] = 39
	b64_index ["o"] = 40
	b64_index ["p"] = 41
	b64_index ["q"] = 42
	b64_index ["r"] = 43
	b64_index ["s"] = 44
	b64_index ["t"] = 45
	b64_index ["u"] = 46
	b64_index ["v"] = 47
	b64_index ["w"] = 48
	b64_index ["x"] = 49
	b64_index ["y"] = 50
	b64_index ["z"] = 51
}

function b64_decode (val,        v, i, offset, len, tmp) {
	v      = 0;
	i      = 0;
	len    = length(val);

	for (i = 1; i <= len; ++i) {
		tmp = b64_index [substr(val, i, 1)];

		if (tmp == ""){
			printf \
				"Illegal character in base64 value: %c\n", \
				substr(val, i, 1) > "/dev/stderr"

			exit 4
		}

		v *= 64
		v += tmp
	}

	return v;
}

BEGIN {
	idx_data_sep = "\034"
	for (i=1; i <= ARGC; ++i){
		if (ARGV [i] == "--help"){
			usage()
			exit 0
		}
		if (ARGV [i] == "--headword-separator"){
			if (i + 2 == ARGC){
				print "missing parameter " ARGV [i] > "/dev/stderr"
				print "run \"dictunformat --help\" for help" > "/dev/stderr"
				exit 1
			}
			separator = ARGV [i+1]

			ARGV [i]   = ""
			ARGV [i+1] = ""

			++i

			continue
		}
		if (ARGV [i] ~ /^--headword-separator=/){
			separator = ARGV [i]
			sub(/^.*=/, "", separator)
			ARGV [i] = ""

			continue
		}
		if (ARGV [i] ~ /^--index-data-separator=/){
			idx_data_sep = ARGV [i]
			sub(/^.*=/, "", idx_data_sep)
			ARGV [i] = ""

			continue
		}
		if (ARGV [i] == "--"){
			ARGV [i] = ""

			++i

			break
		}
		if (ARGV [i] ~ /^[^-]/ || ARGV [i] == "-"){
			break
		}

		print "unknown argument " ARGV [i] > "/dev/stderr"
		print "run \"dictunformat --help\" for help" > "/dev/stderr"
		exit 1
	}

	if (i + 2 != ARGC){
		print "run \"dictunformat --help\" for help" > "/dev/stderr"
		exit 2
	}

	index_fn = ARGV [i]
	ARGV [i] = ""
}

function skip (head_word){
	skipped [head_word] = 1
	gsub(/[^A-Za-z0-9]/, "", head_word)
	skipped [head_word] = 1
}

BEGIN {
	FS = "\t"
	while ((ret = getline < index_fn) > 0 && (NF == 3 || NF == 4)){
		offset    = b64_decode($2)
		if (NF > 3){
			head_word = ($1 idx_data_sep $4)
		}else{
			head_word = $1
		}

		if (offset in offs2word){
			offs2word [offset] = \
				offs2word [offset] SUBSEP head_word
		}else{
			offs2word [offset] = head_word
		}
	}

	if (ret < 0){
		print "index file reading error" > "/dev/stderr"
		exit 4
	}

	if (NF != 3 && NF != 4){
		print "index file format error" > "/dev/stderr"
		exit 5
	}

	skip("00-database-utf8")
	skip("00-database-8bit")
	skip("00-database-8bit-new")
	skip("00-database-allchars")
	skip("00-database-alphabet")
	skip("00-database-default-strategy")
	skip("00-database-mime-header")
	skip("00-database-case-sensitive")
	skip("00-database-dictfmt")

	offset  = 0
}

{
	if (offset in offs2word){
		hw = offs2word [offset]
		hw_is_skipped = (hw in skipped) || hw ~ /^00-?database-?dictfmt/
		if (!hw_is_skipped){
			gsub(SUBSEP, separator, hw)
			printf "_____\n\n%s\n", hw
		}
	}

	if (!hw_is_skipped)
		print $0

	offset += length($0) + NL_size
}
' "$@" -