diff options
Diffstat (limited to 'ipl/progs/idxtext.icn')
| -rw-r--r-- | ipl/progs/idxtext.icn | 155 |
1 files changed, 155 insertions, 0 deletions
diff --git a/ipl/progs/idxtext.icn b/ipl/progs/idxtext.icn new file mode 100644 index 0000000..c31bae0 --- /dev/null +++ b/ipl/progs/idxtext.icn @@ -0,0 +1,155 @@ +############################################################################ +# +# File: idxtext.icn +# +# Subject: Program for creating indexed text-base +# +# Author: Richard L. Goerwitz +# +# Date: July 9, 1991 +# +############################################################################ +# +# This file is in the public domain. +# +############################################################################ +# +# Version: 1.15 +# +############################################################################ +# +# idxtext turns a file associated with gettext() routine into an +# indexed text-base. Though gettext() will work fine with files +# that haven't been indexed via idxtext(), access is faster if the +# indexing is done if the file is, say, over 10k (on my system the +# crossover point is actually about 5k). +# +# Usage is simply "idxtext [-a] file1 [file2 [...]]," where file1, +# file2, etc are the names of gettext-format files that are to be +# (re-)indexed. The -a flag tells idxtext to abort if an index file +# already exists. +# +# Indexed files have a very simple format: keyname delimiter offset +# [delimiter offset [etc.]]\n. The first line of the index file is a +# pointer to the last indexed byte of the text-base file it indexes. +# +# BUGS: Index files are too large. Also, I've yet to find a portable +# way of creating unique index names that are capable of being +# uniquely identified with their original text file. It might be +# sensible to hard code the name into the index. The chances of a +# conflict seem remote enough that I haven't bothered. If you're +# worried, use the -a flag. (RLG) +############################################################################ +# +# Links: adjuncts +# +# Tested with: MS-DOS, MS-DOS/386, OS/2, ProIcon, UNIX +# +# See also: gettext.icn +# +# Modified by Phillip Lee Thomas +# History: modified link and local statements. +# modified to run under OS/2 and ProIcon. +# Added exit() statement. +# Move OS declarations to Set_OS() in adjuncts.icn. +# Allow multiple indexed values. +# +# Version 1.15 (August 5, 1995) +# Use preprocessor include statement rather than link. +# Allow multiple index keys for a stretch of text: +# Example: +# ::key one ::key two ::another key +# Multiple lines of text which are retrieved +# by searching for these three keys. +# ::key for another stretch of text +# A second bit of text. +# +# +############################################################################ +# +# Links: adjuncts +# +############################################################################ + +link adjuncts + +# declared in adjuncts.icn +# global _slash, _baselen, _delimiter + +procedure main(a) + + local ABORT, idxfile_name, fname, infile, outfile + + Set_OS() + + if \a[1] == "-a" then ABORT := pop(a) + + # Check to see if we have any arguments. + + if find("Macintosh", &features) then { + writes("Enter file name for indexing: ") + a := [read()] + } + else { + *a = 0 & stop("usage: idxtext [-a] file1 [file2 [...]]") + } + + # Start popping filenames off of the argument list. + + while fname := pop(a) do { + + # Open input file. + + infile := open(fname) | + { write(&errout, "idxtext: ",fname," not found"); next } + + # Get index file name. + + idxfile_name := Pathname(fname) || getidxname(fname) + if \ABORT then if close(open(idxfile_name)) then + stop("idxtext: index file ",idxfile_name, " already exists") + outfile := open(idxfile_name, "w") | + stop("idxtext: can't open ", idxfile_name) + + # Write index to index.IDX file. + + write_index(infile, outfile) + every close(infile | outfile) + } + exit() +end + + +procedure write_index(in, out) + + local key_offset_table, w, line, KEY + + # Write to out all keys in file "in," with their byte + # offsets. + + key_offset_table := table() + + while (w := where(in), line := read(in)) do { + line ? { + while ="::" do { + KEY := trim(tab(find("::") | 0)) + if not (/key_offset_table[KEY] := KEY || _delimiter || w) + then key_offset_table[KEY] ||:= _delimiter || w + } + } + } + + # First line of index contains the offset of the last + # indexed byte in write_index, so that we can still + # search unindexed parts of in. + + write(out, where(in)) + + # Write sorted KEY\toffset lines. + + if *key_offset_table > 0 then { + every write(out, (!sort(key_offset_table))[2]) + return + } + else stop("No indexed items found.") +end |