Source Code 1992 March/Source_Code_CD-ROM_Walnut_Creek_March_1992.iso/usenet/altsrcs/3/3587

Text File | 1991-07-02 | 20KB | 656 lines

Newsgroups: alt.sources
From: [e-mail] (Richard L. Goerwitz)
Subject: kjv browser, part 7 of 11
Message-ID: <[e-mail]>
Date: Wed, 3 Jul 1991 06:51:59 GMT

---- Cut Here and feed the following to sh ----
#!/bin/sh
# this is bibleref.07 (part 7 of a multipart archive)
# do not concatenate these parts, unpack them in order with /bin/sh
# file iscreen.icn continued
#
if test ! -r _shar_seq_.tmp; then
    echo 'Please unpack part 1 first!'
    exit 1
fi
(read Scheck
 if test "$Scheck" != 7; then
    echo Please unpack part "$Scheck" next!
    exit 1
 else
    exit 0
 fi
) < _shar_seq_.tmp || exit 1
if test ! -f _shar_wnt_.tmp; then
    echo 'x - still skipping iscreen.icn'
else
echo 'x - continuing file iscreen.icn'
sed 's/^X//' << 'SHAR_EOF' >> 'iscreen.icn' &&
X#
X#    Author:     Richard L. Goerwitz
X#
X#    Version: 1.26
X#
X############################################################################
X#
X#  This and future version of iscreen are placed in the public domain - RLG
X#
X############################################################################
X#
X#      This file contains some rudimentary screen functions for use with
X#  itlib.icn (termlib-like routines for Icon).
X#
X#      clear()              - clears the screen (tries several methods)
X#      emphasize()          - initiates emphasized mode
X#      boldface()           - initiates bold mode
X#      blink()              - initiates blinking mode
X#      normal()             - resets to normal mode
X#      message(s)           - displays message s on 2nd-to-last line
X#      underline()          - initiates underline mode
X#      status_line(s,s2,p)  - draws status line s on the 3rd-to-last
X#        screen line; if s is too short for the terminal, s2 is used;
X#        if p is nonnull then it either centers, left-, or right-justi-
X#        fies, depending on the value, "c," "l," or "r."
X#      clear_emphasize()    - horrible way of clearing the screen to all-
X#        emphasize mode; necessary for many terminals
X#
X############################################################################
X#
X#  Requires: UNIX
X#
X#  Links: itlib.icn (or your OS-specific port of itlib)
X#
X#  See also: boldface.icn
X#
X############################################################################
X
X
Xprocedure clear()
X
X    # Clears the screen.  Tries several methods.
X    local i
X
X    normal()
X    if not iputs(getval("cl"))
X    then iputs(igoto(getval("cm"),1,1) | getval("ho"))
X    if not iputs(getval("cd"))
X    then {
X    every i := 1 to getval("li") do {
X        iputs(igoto(getval("cm"),1,i))
X        iputs(getval("ce"))
X    }
X    iputs(igoto(getval("cm"),1,1))
X    }
X    return
X
Xend
X
X
X
Xprocedure boldface()
X
X    static bold_str, cookie_str
X    initial {
X    if bold_str := getval("md")
X    then cookie_str := repl(getval("le"|"bc") | "\b", getval("mg"))
X    else {
X        # One global procedure value substituted for another.
X        boldface := emphasize
X        return emphasize()
X    }
X    }
X
X    normal()
X    iputs(\bold_str)
X    iputs(\cookie_str)
X    return
X
Xend
X
X
X
Xprocedure blink()
X
X    static blink_str, cookie_str
X    initial {
X    if blink_str := getval("mb")
X    then cookie_str :=
X         repl(getval("le"|"bc") | "\b", getval("mg"))
X    else {
X        # One global procedure value substituted for another.
X        blink := emphasize
X        return emphasize()
X    }
X    }
X
X    normal()
X    iputs(\blink_str)
X    iputs(\cookie_str)
X    return
X
Xend
X
X
X
Xprocedure emphasize()
X
X    static emph_str, cookie_str
X    initial {
X    if emph_str := getval("so")
X    then cookie_str := repl(getval("le"|"bc") | "\b", getval("sg"))
X    else {
X        if emph_str := getval("us")
X        then cookie_str := repl(getval("le"|"bc") | "\b", getval("ug"))
X    }
X    }
X
X    normal()
X    iputs(\emph_str)
X    iputs(\cookie_str)
X    return
X
Xend
X
X
X
Xprocedure underline()
X
X    static underline_str, cookie_str
X    initial {
X    if underline_str := getval("us")
X    then cookie_str := repl(getval("le"|"bc") | "\b", getval("ug"))
X    }
X
X    normal()
X    iputs(\underline_str)
X    iputs(\cookie_str)
X    return
X
Xend
X
X
X
Xprocedure normal(mode)
X
X    static UN_emph_str, emph_cookie_str,
X    UN_underline_str, underline_cookie_str,
X    UN_bold_str, bold_cookie_str
X
X    initial {
X
X    # Find out code to turn off emphasize (reverse video) mode.
X    if UN_emph_str := getval("se") then
X        # Figure out how many backspaces we need to erase cookies.
X        emph_cookie_str := repl(getval("le"|"bc") | "\b", getval("sg"))
X
X    # Finally, figure out how to turn off underline mode.
X    if UN_underline_str := (UN_emph_str ~== getval("ue")) then
X        underline_cookie_str := repl(getval("le"|"bc")|"\b", getval("ug"))
X
X    # Figure out how to turn off boldface mode.
X    if UN_bold_str :=
X        (UN_underline_str ~== (UN_emph_str ~== getval("me"))) then
X        # Figure out how many backspaces we need to erase cookies.
X        bold_cookie_str := repl(getval("le"|"bc") | "\b", getval("mg"))
X
X    }
X
X    iputs(\UN_emph_str) &
X    iputs(\emph_cookie_str)
X
X    iputs(\UN_underline_str) &
X    iputs(\underline_cookie_str)
X
X    iputs(\UN_bold_str) &
X    iputs(\bold_cookie_str)
X
X    return
X
Xend
X
X
X
Xprocedure status_line(s,s2,p)
X
X    # Writes a status line on the terminal's third-to-last line
X    # The only necessary argument is s.  S2 (optional) is used
X    # for extra narrow screens.  In other words, by specifying
X    # s2 you give status_line an alternate, shorter status string
X    # to display, in case the terminal isn't wide enough to sup-
X    # port s.  If p is nonnull, then the status line is either
X    # centered (if equal to "c"), left justified ("l"), or right
X    # justified ("r").
X
X    local width
X
X    /s := ""; /s2 := ""; /p := "c"
X    width := getval("co")
X    if *s > width then {
X    (*s2 < width, s := s2) |
X        er("status_line","Your terminal is too narrow.",4)
X    }
X
X    case p of {
X    "c"    : s := center(s,width)
X    "l"    : s := left(s,width)
X    "r"    : s := right(s,width)
X    default: stop("status_line:  Unknown option "||string(p),4)
X    }
X
X    iputs(igoto(getval("cm"), 1, getval("li")-2))
X    emphasize(); writes(s)
X    normal()
X    return
X
Xend
X
X
X
Xprocedure message(s)
X
X    # Display prompt s on the second-to-last line of the screen.
X    # I hate to use the last line, due to all the problems with
X    # automatic scrolling.
X
X    /s := ""
X    normal()
X    iputs(igoto(getval("cm"), 1, getval("li")))
X    iputs(getval("ce"))
X    normal()
X    iputs(igoto(getval("cm"), 1, getval("li")-1))
X    iputs(getval("ce"))
X    writes(s[1:getval("co")] | s)
X    return
X
Xend
X
X
X
Xprocedure clear_underline()
X
X    # Horrible way of clearing the screen to all underline mode, but
X    # the only apparent way we can do it "portably" using the termcap
X    # capability database.
X
X    local i
X
X    underline()
X    iputs(igoto(getval("cm"),1,1))
X    if getval("am") then {
X    underline()
X        every 1 to (getval("li")-1) * getval("co") do
X        writes(" ")
X    }
X    else {
X    every i := 1 to getval("li")-1 do {
X        iputs(igoto(getval("cm"), 1, i))
X        underline()
X        writes(repl(" ",getval("co")))
X    }
X    }
X    iputs(igoto(getval("cm"),1,1))
X
Xend
X
X
X
Xprocedure clear_emphasize()
X
X    # Horrible way of clearing the screen to all reverse-video, but
X    # the only apparent way we can do it "portably" using the termcap
X    # capability database.
X
X    local i
X
X    emphasize()
X    iputs(igoto(getval("cm"),1,1))
X    if getval("am") then {
X    emphasize()
X        every 1 to (getval("li")-1) * getval("co") do
X        writes(" ")
X    }
X    else {
X    every i := 1 to getval("li")-1 do {
X        iputs(igoto(getval("cm"), 1, i))
X        emphasize()
X        writes(repl(" ",getval("co")))
X    }
X    }
X    iputs(igoto(getval("cm"),1,1))
X
Xend
SHAR_EOF
echo 'File iscreen.icn is complete' &&
true || echo 'restore of iscreen.icn failed'
rm -f _shar_wnt_.tmp
fi
# ============= findre.icn ==============
if test -f 'findre.icn' -a X"$1" != X"-c"; then
    echo 'x - skipping findre.icn (File already exists)'
    rm -f _shar_wnt_.tmp
else
> _shar_wnt_.tmp
echo 'x - extracting findre.icn (Text)'
sed 's/^X//' << 'SHAR_EOF' > 'findre.icn' &&
X########################################################################
X#
X#    Name:    findre.icn
X#
X#    Title:    "Find" Regular Expression
X#
X#    Author:    Richard L. Goerwitz
X#
X#    Version: 1.15
X#
X########################################################################
X#
X#  I place this and any later versions in the public domain - RLG.
X#
X########################################################################
X#
X#  DESCRIPTION:  findre() is like the Icon builtin function find(),
X#  except that it takes, as its first argument, a regular expression
X#  pretty much like the ones the Unix egrep command uses (the few
X#  minor differences are listed below).  Its syntax is the same as
X#  find's (i.e. findre(s1,s2,i,j)), with the exception that a no-
X#  argument invocation wipes out all static structures utilized by
X#  findre, and then forces a garbage collection.
X#
X#  (For those not familiar with regular expressions and the Unix egrep
X#  command: findre() offers a simple and compact wildcard-based search
X#  system.  If you do a lot of searches through text files, or write
X#  programs which do searches based on user input, then findre is a
X#  utility you might want to look over.)
X#
X#  IMPORTANT DIFFERENCES between find and findre:  As noted above,
X#  findre() is just a find() function that takes a regular expression
X#  as its first argument.  One major problem with this setup is that
X#  it leaves the user with no easy way to tab past a matched
X#  substring, as with
X#
X#    s ? write(tab(find("hello")+5))
X#
X#  In order to remedy this intrinsic deficiency, findre() sets the
X#  global variable __endpoint to the first position after any given
X#  match occurs.  Use this variable with great care, preferably
X#  assigning its value to some other variable immediately after the
X#  match (for example, findre("hello [.?!]*",s) & tmp := __endpoint).
X#  Otherwise, you will certainly run into trouble.  (See the example
X#  below for an illustration of how __endpoint is used).
X#
X#  IMPORTANT DIFFERENCES between egrep and findre:  findre utilizes
X#  the same basic language as egrep.  The only big difference is that
X#  findre uses intrinsic Icon data structures and escaping conven-
X#  tions rather than those of any particular Unix variant.  Be care-
X#  ful!  If you put findre("\(hello\)",s) into your source file,
X#  findre will treat it just like findre("(hello)",s).  If, however,
X#  you enter '\(hello\)' at run-time (via, say, findre(!&input,s)),
X#  what Icon receives will depend on your operating system (most
X#  likely, a trace will show "\\(hello\\)").
X#
X#  BUGS:  Space has essentially been conserved at the expense of time
X#  in the automata produced by findre().  The algorithm, in other
X#  words, will produce the equivalent of a pushdown automaton under
X#  certain circumstances, rather than strive (at the expense of space)
X#  for full determinism.  I tried to make up a nfa -> dfa converter
X#  that would only create that portion of the dfa it needed to accept
X#  or reject a string, but the resulting automaton was actually quite
X#  slow (if anyone can think of a way to do this in Icon, and keep it
X#  small and fast, please let us all know about it).  Note that under
X#  version 8 of Icon, findre takes up negligible storage space, due to
X#  the much improved hashing algorithm.  I have not tested it under
X#  version 7, but I would expect it to use up quite a bit more space
X#  in that environment.
X#
X#  IMPORTANT NOTE:  Findre takes a shortest-possible-match approach
X#  to regular expressions.  In other words, if you look for "a*",
X#  findre will not even bother looking for an "a."  It will just match
X#  the empty string.  Without this feature, findre would perform a bit
X#  more slowly.  The problem with such an approach is that often the
X#  user will want to tab past the longest possible string of matched
X#  characters (say tab((findre("a*|b*"), __endpoint)).  In circumstan-
X#  ces like this, please just use something like:
X#
X#      s ? {
X#          tab(find("a")) &  # or use Arb() from the IPL (patterns.icn)
X#          tab(many('a'))
X#          tab(many('b'))
X#      }
X#
X#  or else use some combination of findre and the above.
X#
X########################################################################
X#
X#  REGULAR EXPRESSION SYNTAX: Regular expression syntax is complex,
X#  and yet simple.  It is simple in the sense that most of its power
X#  is concentrated in about a dozen easy-to-learn symbols.  It is
X#  complex in the sense that, by combining these symbols with
X#  characters, you can represent very intricate patterns.
X#
X#  I make no pretense here of offering a full explanation of regular
X#  expressions, their usage, and the deeper nuances of their syntax.
X#  As noted above, this should be gleaned from a Unix manual.  For
X#  quick reference, however, I have included a brief summary of all
X#  the special symbols used, accompanied by an explanation of what
X#  they mean, and, in some cases, of how they are used (most of this
X#  is taken from the comments prepended to Jerry Nowlin's Icon-grep
X#  command, as posted a couple of years ago):
X#
X#     ^   -  matches if the following pattern is at the beginning
X#            of a line (i.e. ^# matches lines beginning with "#")
X#     $   -  matches if the preceding pattern is at the end of a line
X#     .   -  matches any single character
X#     +   -  matches from 1 to any number of occurrences of the
X#            previous expression (i.e. a character, or set of paren-
X#            thesized/bracketed characters)
X#     *   -  matches from 0 to any number of occurrences of the previous
X#            expression
X#     \   -  removes the special meaning of any special characters
X#            recognized by this program (i.e if you want to match lines
X#            beginning with a "[", write ^\[, and not ^[)
X#     |   -  matches either the pattern before it, or the one after
X#            it (i.e. abc|cde matches either abc or cde)
X#     []  -  matches any member of the enclosed character set, or,
X#            if ^ is the first character, any nonmember of the
X#            enclosed character set (i.e. [^ab] matches any character
X#         _except_ a and b).
X#     ()  -  used for grouping (e.g. ^(abc|cde)$ matches lines consist-
X#            ing of either "abc" or "cde," while ^abc|cde$ matches
X#            lines either beginning with "abc" or ending in "cde")
X#
X#########################################################################
X#
X#  EXAMPLE program:
X#
X#  procedure main(a)
X#      while line := !&input do {
X#          token_list := tokenize_line(line,a[1])
X#          every write(!token_list)
X#      }
X#  end
X#
X#  procedure tokenize_line(s,sep)
X#      tmp_lst := []
X#      s ? {
X#          while field := tab(findre(sep)|0) &
X#          mark := __endpoint
X#          do {
X#              put(tmp_lst,"" ~== field)
X#              if pos(0) then break
X#              else tab(mark)
X#          }
X#      }
X#      return tmp_lst
X#  end
X#
X#  The above program would be compiled with findre (e.g. "icont
X#  test_prg.icn findre.icn") to produce a single executable which
X#  tokenizes each line of input based on a user-specified delimiter.
X#  Note how __endpoint is set soon after findre() succeeds.  Note
X#  also how empty fields are excluded with "" ~==, etc.  Finally, note
X#  that the temporary list, tmp_lst, is not needed.  It is included
X#  here merely to illustrate one way in which tokens might be stored.
X#
X#  Tokenizing is, of course, only one of many uses one might put
X#  findre to.  It is very helpful in allowing the user to construct
X#  automata at run-time.  If, say, you want to write a program that
X#  searches text files for patterns given by the user, findre would be
X#  a perfect utility to use.  Findre in general permits more compact
X#  expression of patterns than one can obtain using intrinsic Icon
X#  scanning facilities.  Its near complete compatibility with the Unix
X#  regexp library, moreover, makes for greater ease of porting,
X#  especially in cases where Icon is being used to prototype C code.
X#
X#########################################################################
X
X
Xglobal state_table, parends_present, slash_present
Xglobal biggest_nonmeta_str, __endpoint
Xrecord o_a_s(op,arg,state)
X
X
Xprocedure findre(re, s, i, j)
X
X    local p, x, nonmeta_len, tokenized_re, tmp
X    static FSTN_table, STRING_table
X    initial {
X    FSTN_table := table()
X    STRING_table := table()
X    }
X
X    if /re then {
X    FSTN_table := table()
X    STRING_table := table()
X    collect()  # do it *now*
X    return
X    }
X
X    /s := &subject
X    if \i then {
X    if i < 1 then
X        i := *s + (i+1)
X    }
X    else i := \&pos | 1
X    if \j then {
X    if j < 1 then
X        j := *s + (j+1)
X    }
X
X    else j := *s+1
X    if /FSTN_table[re] then {
X    # If we haven't seen this re before, then...
X    if \STRING_table[re] then {
X        # ...if it's in the STRING_table, use plain find()
X        every p := find(STRING_table[re],s,i,j)
X        do { __endpoint := p + *STRING_table[re]; suspend p }
X        fail
X    }
X    else {
X        # However, if it's not in the string table, we have to
X        # tokenize it and check for metacharacters.  If it has
X        # metas, we create an FSTN, and put that into FSTN_table;
X        # otherwise, we just put it into the STRING_table.
X        tokenized_re := tokenize(re)
X        if 0 > !tokenized_re then {
X        # if at least one element is < 0, re has metas
X        MakeFSTN(tokenized_re) | err_out(re,2)
X        # both biggest_nonmeta_str and state_table are global
X        /FSTN_table[re] := [.biggest_nonmeta_str, copy(state_table)]
X        }
X        else {
X        # re has no metas; put the input string into STRING_table
X        # for future reference, and execute find() at once
X        tmp := ""; every tmp ||:= char(!tokenized_re)
X        insert(STRING_table,re,tmp)
X        every p := find(STRING_table[re],s,i,j)
X        do { __endpoint := p + *STRING_table[re]; suspend p }
X        fail
X        }
X    }
X    }
X
X
X    if nonmeta_len := (1 < *FSTN_table[re][1]) then {
X    # If the biggest non-meta string in the original re
X    # was more than 1, then put in a check for it...
X    s[1:j] ? {
X        tab(x := i to j - nonmeta_len) &
X        (find(FSTN_table[re][1]) | fail) \ 1 &
X        (__endpoint := apply_FSTN(&null,FSTN_table[re][2])) &
X        (suspend x)
X    }
X    }
X    else {
X    #...otherwise it's not worth worrying about the biggest nonmeta str
X    s[1:j] ? {
X        tab(x := i to j) &
X        (__endpoint := apply_FSTN(&null,FSTN_table[re][2])) &
X        (suspend x)
X    }
X    }
X
Xend
X
X
X
Xprocedure apply_FSTN(ini,tbl)
X
X    local biggest_pos, POS, tmp, fin
X    static s_tbl
X
X    /ini := 1 & s_tbl := tbl & biggest_pos := 1
X    if ini = 0 then {
X    return &pos
X    }
X    POS := &pos
X    fin := 0
X
X    repeat {
X    if tmp := !s_tbl[ini] &
X        tab(tmp.op(tmp.arg))
X    then {
X        if tmp.state = fin
X        then return &pos
X        else ini := tmp.state
X    }
X    else (&pos := POS, fail)
X    }
X
Xend
X
X
X
Xprocedure tokenize(s)
X
X    local token_list, chr, tmp, b_loc, next_one, fixed_length_token_list, i
X
X    token_list := list()
X    s ? {
X    tab(many('*+?|'))
X    while chr := move(1) do {
X        if chr == "\\"
X        # it can't be a metacharacter; remove the \ and "put"
X        # the integer value of the next chr into token_list
X        then put(token_list,ord(move(1))) | err_out(s,2,chr)
X        else if any('*+()|?.$^',chr)
X        then {
X        # Yuck!  Egrep compatibility stuff.
X        case chr of {
X            "*"    : {
X            tab(many('*+?'))
X            put(token_list,-ord("*"))
X            }
X            "+"    : {
SHAR_EOF
true || echo 'restore of findre.icn failed'
fi
echo 'End of  part 7'
echo 'File findre.icn is continued in part 8'
echo 8 > _shar_seq_.tmp
exit 0
--

   -Richard L. Goerwitz              [e-mail]
   [e-mail]         rutgers!oddjob!gide!sophist!goer