home *** CD-ROM | disk | FTP | other *** search
- #!/usr/local/bin/gawk -f
- # @(#) ucomm.gawk 1.1 96/05/30
- # 94/12/27 john h. dubois iii (john@armory.com)
- # 96/03/27 Let 0 or 1 args be given.
- # 96/04/01 Added &taAdLiIpP options.
- # ucomm: a generalized 'comm' that does not require the files to be sorted.
-
- ### Start of setup blocks
- BEGIN {
- Name = "ucomm"
- Usage = "Usage: " Name " [-aAdhiIlLnox] [-<field-num>] [-t<field-sep>]\n"\
- " [-p<pattern>|-P<pattern>] selector[,selector...] "\
- "[file1 file2 ...]"
- ARGC = Opts(Name,Usage,"aAdhiIlLnop:P:x&>t:",0)
- if ((Err = ExclusiveOptions("p,P;l,n;a,A,d;L,d",Options)) != "") {
- printf "Error: %s\n",Err > "/dev/stderr"
- Err = 1
- exit(1)
- }
- if ("h" in Options) {
- printf \
- "%s: show which files lines occur in.\n"\
- " %s takes a list of common-line selectors and a list of filenames and\n"\
- "shows lines from the files that are selected. Selectors have the form\n"\
- "nn... where each n is a digit or letter specifying a file number. 1\n"\
- "refers to the first file given on the command line, 2 to the second, etc.\n"\
- "The letter 'a' refers to the 10th, and 'z' to the 35th. Each selector\n"\
- "causes lines that occur in all of the files whose numbers are in the\n"\
- "selector, and which occur only in those files, to be printed. If the line\n"\
- "occurs in any files whose number is not in the selector, the selector will\n"\
- "not cause it to be printed, though another selector might. File numbers\n"\
- "higher than the number of filenames given are ignored with a warning.\n"\
- " A range of file numbers may be given as part of a selector. For\n"\
- "example, the selector 13-c would specify file 1 and files 3 through c\n"\
- "inclusive. $ refers to the last file on the command line. A file number\n"\
- "of '%%' is short for 1,2,...9,a,...z; that is, it causes any line which\n"\
- "occurs in only one file to be printed. If any other file numbers are\n"\
- "included with a '%%' selector, then any lines that occurs in all of the\n"\
- "specifically named files, plus one other, are selected. '~' complements a\n"\
- "selector with respect to the set of all file numbers. It can be given\n"\
- "anywhere in a selector. If given by itself, it is equivalent to 1-$,\n"\
- "which causes any line which occurs in all files to be printed. If any\n"\
- "other file numbers are included with a '~' selector, then any lines that\n"\
- "occur in all files except those specifically named are selected. '*' will\n"\
- "cause all lines to be selected. If a selector begins with '!' or '^', it\n"\
- "will suppress printing of lines that it selects even if other selectors\n"\
- "would cause them to be printed. An example of its use would be the\n"\
- "selector '*,!~' which would print all lines except those that occur in all\n"\
- "of the files. Note that various of the characters $~*!^ are special to\n"\
- "the shell and need to be quoted or escaped.\n"\
- " If more than one selector is given, each output line is prefixed by\n"\
- "the selector that caused it to be printed followed by a colon and a space.\n"\
- "For example: \n"\
- "13ac: this is a line that occurs in files 1, 3, a, and c\n"\
- "The selector part of the line prefix is effectively be a list of the files\n"\
- "the line was found in. No line is printed more than once, even if it\n"\
- "occurs more than once in a file. The order of the output lines is not the\n"\
- "same as the order in which lines are read.\n"\
- "The file name /dev/stdin can be used for the standard input, and /dev/fd/n\n"\
- "can be used for file descriptor n. If no filenames are given or only one\n"\
- "filename is given, no selector may be given; a single instance of each\n"\
- "line that occurs in the file or in the standard input respectively is\n"\
- "printed.\n"\
- "%s\n"\
- "Other options:\n"\
- "-[pP]<pattern>: In all input files, ignore (discard) all lines that do not\n"\
- " (-p) or do (-P) match <pattern>, which is in the style of egrep(C).\n"\
- "-i: Ignore case when determining uniqueness of lines.\n"\
- "-I: Ignore case in pattern matches used for -[pP].\n"\
- "-h: Print this help.\n"\
- "-l: Make the selected-line prefix consist only of file numbers. If a\n"\
- " selector includes a range or one of the special characters [$%%~!^*],\n"\
- " they are converted into file numbers.\n"\
- "-n: Do not prefix output lines with the selector.\n"\
- "-o: Retain line order. In the output, lines are printed in the same order\n"\
- " as they were first encountered in the input. This option is expensive\n"\
- " in terms of memory use.\n"\
- "-x: Print debugging info, including expanded versions of given selectors.\n"\
- "-<field-num>: Check only the given field number of each line when\n"\
- " comparing them to others for uniqueness. Fields are separated by\n"\
- " whitespace (tabs and blanks). If a line begins with whitespace, the\n"\
- " first field is the string that occurs between the initial whitespace\n"\
- " and the next instance of whitespace (or the end of the line). In the\n"\
- " output, by default the first instance of the line is printed.\n"\
- "The rest of the options are used only when -<field-num> is given:\n"\
- "-a: Print all unique lines selected by -<field-num>.\n"\
- "-A: Like -a, except that a blank line is printed between each set of lines\n"\
- " that have the same field.\n"\
- "-L: Used with -a or -A; prefix each line with the numbers of the files the\n"\
- " line was found in.\n"\
- "-d: Print only the field that is being checked, not the whole line.\n"\
- "-t<field-sep>: Set the field separator to <field-sep>. <field-sep> is a\n"\
- " pattern in the style of egrep(C). If this option is given and a line\n"\
- " begins with a string that matches the pattern, the first field is\n"\
- " empty and the second field occurs after the initial matched characters.\n"\
- " Thus, -t'[ \\t]+' is different from the default field separator in the\n"\
- " way that fields on a line that begins with whitespace are numbered.\n",
- Name,Name,Usage
- exit 0
- }
- if (ARGC == 3) {
- print Name ": Wrong number of arguments. Use -h for help.\n"\
- Usage > "/dev/stderr"
- exit 1
- }
- if (ARGC > 3)
- NumFiles = ARGC - 2 # Skip program name & selector
- else {
- # If 1 arg (ARGC = 2) is given, it is a filename.
- if (ARGC == 1) # If 0 args, make input be stdin
- ARGV[2] = "/dev/stdin"
- else
- ARGV[2] = ARGV[1] # move filename to correct place
- # If 0 or 1 args, set selector to 1 and # of files to 1
- NumFiles = 1
- ARGV[1] = "1"
- ARGC = 3 # for gawk
- }
- if (NumFiles > 35) { # 1-9a-z = 35
- print "Cannot process more than 35 files." > "/dev/stderr"
- exit 1
- }
- # Char n of this string is the fileno char for file n
- AllNums = substr("123456789abcdefghijklmnopqrstuvwxyz",1,NumFiles)
- if ((NumSel = ProcSelectors(ARGV[1],Selectors,UnSelectors)) == -1)
- exit 1
- if (NumSel == 0) {
- print "No selectors." > "/dev/stderr"
- Err = "0"
- }
- if (Err != "")
- exit Err
- ARGV[1] = "/dev/null" # skip selector arg
- Ordered = "o" in Options
- if (GotPat = ("p" in Options || "P" in Options)) {
- if ("p" in Options)
- Pat = Options["p"]
- if ("P" in Options)
- NotPat = Options["P"]
- }
- if ("&" in Options) {
- FieldNum = Options["&"]
- WholeLine = !("d" in Options) # So whole line will be printed
- # If this is on, WholeLine is too
- AllLines = "a" in Options || "A" in Options
- SeparateLines = "A" in Options
- PrefixEachLine = "L" in Options
- }
- else
- FieldNum = 0 # Compare entire line
- if ("t" in Options)
- FS = Options["t"]
- if (Debug = ("x" in Options)) {
- print "Field number: " FieldNum
- print "Field sep: " FS
- print "Selectors:" > "/dev/stderr"
- for (i in Selectors)
- print i > "/dev/stderr"
- print "Exclusion selectors:" > "/dev/stderr"
- for (i in UnSelectors)
- print i > "/dev/stderr"
- }
- IGNORECASE = "I" in Options
- if ("i" in Options) {
- NoCase = 1
- # If not working with fields and case is being ignored, turn on
- # Ordered option because it will cause case to be saved as a side
- # effect.
- if (FieldNum == 0)
- Ordered = 1
- }
- }
-
- # Returns the number of selectors, or -1 if a fatal error is encountered
- function ProcSelectors(SelString,Selectors,UnSelectors,
- i,NSel,Sels,Sel,c,Not,Bad,Err,NumSel) {
- NSel = split(SelString,Sels,",")
- for (i = 1; i <= NSel; i++) {
- Sel = tolower(Sels[i]) # Let A-Z also work
- if (Not = ((c = substr(Sel,1,1)) == "!" || c == "^"))
- Sel = substr(Sel,2)
- if (Sel == "") # Empty selector; ignore it
- continue
- if (Sel !~ /^[-1-9a-z$%~*]+$/) {
- Bad = Sel
- gsub(/[-1-9a-z$%~*]+/,"",Bad)
- printf "Invalid character(s) in selector \"%s\": %s\n",
- Sel,Bad > "/dev/stderr"
- Err = 1
- continue
- }
- if (!Not)
- NumSel++
- if (Not) # Can't use ternary operator to select an array
- Err = ExpandSel(Sel,UnSelectors) || Err
- else
- Err = ExpandSel(Sel,Selectors) || Err
- }
- if ("*" in UnSelect) {
- print "* is not valid in an exclusion selector." > "/dev/stderr"
- Err = 1
- }
- return Err ? -1 : NumSel
- }
-
- # Expands selector Sel into a simple selector and makes it an index of SelSet,
- # with the value being the original selector.
- # All selectors put in SelSet will consist of of a sorted sequence of valid
- # file number characters, except that the special selector '*' is stored to
- # indicate that all lines should be selected.
- function ExpandSel(Sel,SelSet,
- i,c,len,Set,Not,One,LastC,RangeStart,RangeEnd,Err,ExpSel,RangeC) {
- Err = 0
- len = length(Sel)
- for (i = 1; i <= len; i++) {
- c = substr(Sel,i,1)
- if (c == "$") # Replace $ with number of last file
- c = Num2FileChar(NumFiles)
- if (c ~ /[1-9a-z]/) {
- if (!FileChar2Num(c))
- printf \
- "Warning: selector char '%s': Not that many files given on command line.\n",
- c > "/dev/stderr"
- # If we are expecting the 2nd char of a range
- if (RangeStart > 0) {
- if (!(RangeEnd = FileChar2Num(c))) {
- print "Invalid character in selector range: %s\n",
- c > "/dev/stderr"
- Err = 1
- }
- else if (RangeEnd < RangeStart) {
- printf "Bad range: %s-%s\n",
- RangeStart,RangeEnd > "/dev/stderr"
- Err = 1
- }
- else for (RangeC = RangeStart+1; RangeC <= RangeEnd; RangeC++)
- Set[Num2FileChar(RangeC)]
- RangeStart = 0
- }
- else
- Set[c]
- }
- # Record that % or ~ was found, for processing at the end
- else if (c == "%")
- One = 1
- else if (c == "~")
- Not = 1
- else if (c == "*")
- SelSet[c] = Sel
- else if (c == "-") { # The last char was the start of a range
- if (!(RangeStart = FileChar2Num(LastC))) {
- print "Invalid character in selector range: %s\n",
- LastC > "/dev/stderr"
- Err = 1
- }
- }
- LastC = c
- }
- if (Not)
- ComplementFiles(Set)
- if (One)
- for (i = 1; i <= NumFiles; i++) {
- c = Num2FileChar(i)
- if (!(c in Set)) {
- Set[c]
- SelSet[Set2Sel(Set)] = Sel
- delete Set[c]
- }
- }
- else {
- ExpSel = Set2Sel(Set)
- if (ExpSel != "")
- SelSet[ExpSel] = Sel
- }
- return Err
- }
-
- function Set2Sel(Set, i,c,ExpSel) {
- for (i = 1; i <= NumFiles; i++)
- if ((c = Num2FileChar(i)) in Set)
- ExpSel = ExpSel c
- return ExpSel
- }
-
- function ComplementFiles(Set, i,c) {
- for (i = 1; i <= NumFiles; i++) {
- c = Num2FileChar(i)
- if (c in Set)
- delete Set[c]
- else
- Set[c]
- }
- }
-
- # Convert numbers 1-35 to chars 1-9a-z
- function Num2FileChar(Num) {
- return substr(AllNums,Num,1)
- }
-
- function FileChar2Num(C) {
- return index(AllNums,C)
- }
-
- ### Start of file processing blocks
-
- # If FileNum is not already part of Lines[Index], add it.
- function AddFileNum(Lines,Index, FFiles) {
- FFiles = Lines[Index] # Get its found-files record
- if (substr(FFiles,length(FFiles),1) != FileNum)
- Lines[Index] = Lines[Index] FileNum
- }
-
- ARGIND != OldInd {
- FileNum = Num2FileChar(ARGIND-1) # First file is arg #2
- OldInd = ARGIND
- }
-
- GotPat {
- if ((Pat != "" && $0 !~ Pat) || (NotPat != "" && $0 ~ NotPat))
- next
- }
-
- # Lines are stored as indexes in Lines[].
- # The value associated with the index is the set of files that the line
- # was found in, first through last.
- # If -o is given, the line is also stored as a value in Order[],
- # with the index being an integer giving the order in which the line was found.
- {
- Index = NoCase ? tolower($FieldNum) : $FieldNum
- if (Index in Lines) { # If the line/field was already seen
- AddFileNum(Lines,Index)
- if (AllLines) {
- if ($0 in TrackWholeLines) {
- if (PrefixEachLine)
- AddFileNum(TrackWholeLines,$0)
- }
- else {
- Field2Line[Index] = Field2Line[Index] "\n" $0
- TrackWholeLines[$0] = FileNum
- }
- }
- }
- else {
- Lines[Index] = FileNum
- if (Ordered)
- Order[++LineCt] = $FieldNum
- if (Debug)
- printf "New field #%d%s: %s\n",FieldNum,
- Ordered ? (" (now " LineCt ")") : "",Index
- if (WholeLine) {
- Field2Line[Index] = $0
- if (AllLines)
- TrackWholeLines[$0] = FileNum
- }
- }
- }
-
- ### Start of report generating blocks
-
- END {
- if (Err != "")
- exit Err
- PrintExpSel = "l" in Options
- if (!(NoSel = "n" in Options)) { # Do not print selectors?
- # If -n wasn't given, print selectors only if at least 2 given.
- # If printing expanded selectors, can't rely on the value NumSel
- # already has, since it counts e.g. % as 1 selector.
- if (PrintExpSel) {
- NumSel = 0
- for (i in Selectors)
- if (++NumSel == 2)
- break
- }
- NoSel = NumSel < 2
- }
- AllSelect = "*" in Selectors
- if (Ordered)
- for (i = 1; i <= LineCt; i++)
- CheckLine(Order[i])
- else
- for (Line in Lines)
- CheckLine(Line)
- }
-
- # If NoCase is true, the indexes in Lines[], TrackWholeLines[],
- # and Field2Line[] are in lowercase.
- function CheckLine(Line, FFiles,nLine,iLines,i,l,Index) {
- Index = NoCase ? tolower(Line) : Line
- FFiles = Lines[Index] # Get this line's found-files record
- if ((AllSelect || FFiles in Selectors) && !(FFiles in UnSelectors)) {
- if (SeparateLines)
- if (NotFirst)
- print ""
- else
- NotFirst = 1
- if (!NoSel)
- printf "%s: ",
- AllSelect ? "*" : (PrintExpSel ? FFiles : Selectors[FFiles])
- if (PrefixEachLine) {
- nLine = split(Field2Line[Index],iLines,"\n")
- for (i = 1; i <= nLine; i++) {
- l = iLines[i]
- printf "%s) %s\n",TrackWholeLines[l],l
- }
- }
- else
- print WholeLine ? Field2Line[Index] : Line
- }
- }
-
- ### Start of library functions
-
- ### Start of ProcArgs library
- # @(#) ProcArgs 1.11 96/12/08
- # 92/02/29 john h. dubois iii (john@armory.com)
- # 93/07/18 Added "#" arg type
- # 93/09/26 Do not count -h against MinArgs
- # 94/01/01 Stop scanning at first non-option arg. Added ">" option type.
- # Removed meaning of "+" or "-" by itself.
- # 94/03/08 Added & option and *()< option types.
- # 94/04/02 Added NoRCopt to Opts()
- # 94/06/11 Mark numeric variables as such.
- # 94/07/08 Opts(): Do not require any args if h option is given.
- # 95/01/22 Record options given more than once. Record option num in argv.
- # 95/06/08 Added ExclusiveOptions().
- # 96/01/20 Let rcfiles be a colon-separated list of filenames.
- # Expand $VARNAME at the start of its filenames.
- # Let varname=0 and -option- turn off an option.
- # 96/05/05 Changed meaning of 7th arg to Opts; now can specify exactly how many
- # of the vars should be searched for in the environment.
- # Check for duplicate rcfiles.
- # 96/05/13 Return more specific error values. Note: ProcArgs() and InitOpts()
- # now return various negatives values on error, not just -1, and
- # Opts() may set Err to various positive values, not just 1.
- # Added AllowUnrecOpt.
- # 96/05/23 Check type given for & option
- # 96/06/15 Re-port to awk
- # 96/10/01 Moved file-reading code into ReadConfFile(), so that it can be
- # used by other functions.
- # 96/10/15 Added OptChars
- # 96/11/01 Added exOpts arg to Opts()
- # 96/11/16 Added ; type
- # 96/12/08 Added Opt2Set() & Opt2Sets()
- # 96/12/27 Added CmdLineOpt()
-
- # optlist is a string which contains all of the possible command line options.
- # A character followed by certain characters indicates that the option takes
- # an argument, with type as follows:
- # : String argument
- # ; Non-empty string argument
- # * Floating point argument
- # ( Non-negative floating point argument
- # ) Positive floating point argument
- # # Integer argument
- # < Non-negative integer argument
- # > Positive integer argument
- # The only difference the type of argument makes is in the runtime argument
- # error checking that is done.
-
- # The & option is a special case used to get numeric options without the
- # user having to give an option character. It is shorthand for [-+.0-9].
- # If & is included in optlist and an option string that begins with one of
- # these characters is seen, the value given to "&" will include the first
- # char of the option. & must be followed by a type character other than ":"
- # or ";".
- # Note that if e.g. &> is given, an option of -.5 will produce an error.
-
- # Strings in argv[] which begin with "-" or "+" are taken to be
- # strings of options, except that a string which consists solely of "-"
- # or "+" is taken to be a non-option string; like other non-option strings,
- # it stops the scanning of argv and is left in argv[].
- # An argument of "--" or "++" also stops the scanning of argv[] but is removed.
- # If an option takes an argument, the argument may either immediately
- # follow it or be given separately.
- # "-" and "+" options are treated the same. "+" is allowed because most awks
- # take any -options to be arguments to themselves. gawk 2.15 was enhanced to
- # stop scanning when it encounters an unrecognized option, though until 2.15.5
- # this feature had a flaw that caused problems in some cases. See the OptChars
- # parameter to explicitly set the option-specifier characters.
-
- # If an option that does not take an argument is given,
- # an index with its name is created in Options and its value is set to the
- # number of times it occurs in argv[].
-
- # If an option that does take an argument is given, an index with its name is
- # created in Options and its value is set to the value of the argument given
- # for it, and Options[option-name,"count"] is (initially) set to the 1.
- # If an option that takes an argument is given more than once,
- # Options[option-name,"count"] is incremented, and the value is assigned to
- # the index (option-name,instance) where instance is 2 for the second occurance
- # of the option, etc.
- # In other words, the first time an option with a value is encountered, the
- # value is assigned to an index consisting only of its name; for any further
- # occurances of the option, the value index has an extra (count) dimension.
-
- # The sequence number for each option found in argv[] is stored in
- # Options[option-name,"num",instance], where instance is 1 for the first
- # occurance of the option, etc. The sequence number starts at 1 and is
- # incremented for each option, both those that have a value and those that
- # do not. Options set from a config file have a value of 0 assigned to this.
-
- # Options and their arguments are deleted from argv.
- # Note that this means that there may be gaps left in the indices of argv[].
- # If compress is nonzero, argv[] is packed by moving its elements so that
- # they have contiguous integer indices starting with 0.
- # Option processing will stop with the first unrecognized option, just as
- # though -- was given except that unlike -- the unrecognized option will not be
- # removed from ARGV[]. Normally, an error value is returned in this case.
- # If AllowUnrecOpt is true, it is not an error for an unrecognized option to
- # be found, so the number of remaining arguments is returned instead.
- # If OptChars is not a null string, it is the set of characters that indicate
- # that an argument is an option string if the string begins with one of the
- # characters. A string consisting solely of two of the same option-indicator
- # characters stops the scanning of argv[]. The default is "-+".
- # argv[0] is not examined.
- # The number of arguments left in argc is returned.
- # If an error occurs, the global string OptErr is set to an error message
- # and a negative value is returned.
- # Current error values:
- # -1: option that required an argument did not get it.
- # -2: argument of incorrect type supplied for an option.
- # -3: unrecognized (invalid) option.
- function ProcArgs(argc,argv,OptList,Options,compress,AllowUnrecOpt,OptChars,
- ArgNum,ArgsLeft,Arg,ArgLen,ArgInd,Option,Pos,NumOpt,Value,HadValue,specGiven,
- NeedNextOpt,GotValue,OptionNum,Escape,dest,src,count,c,OptTerm,OptCharSet)
- {
- # ArgNum is the index of the argument being processed.
- # ArgsLeft is the number of arguments left in argv.
- # Arg is the argument being processed.
- # ArgLen is the length of the argument being processed.
- # ArgInd is the position of the character in Arg being processed.
- # Option is the character in Arg being processed.
- # Pos is the position in OptList of the option being processed.
- # NumOpt is true if a numeric option may be given.
- ArgsLeft = argc
- NumOpt = index(OptList,"&")
- OptionNum = 0
- if (OptChars == "")
- OptChars = "-+"
- while (OptChars != "") {
- c = substr(OptChars,1,1)
- OptChars = substr(OptChars,2)
- OptCharSet[c]
- OptTerm[c c]
- }
- for (ArgNum = 1; ArgNum < argc; ArgNum++) {
- Arg = argv[ArgNum]
- if (length(Arg) < 2 || !((specGiven = substr(Arg,1,1)) in OptCharSet))
- break # Not an option; quit
- if (Arg in OptTerm) {
- delete argv[ArgNum]
- ArgsLeft--
- break
- }
- ArgLen = length(Arg)
- for (ArgInd = 2; ArgInd <= ArgLen; ArgInd++) {
- Option = substr(Arg,ArgInd,1)
- if (NumOpt && Option ~ /[-+.0-9]/) {
- # If this option is a numeric option, make its flag be & and
- # its option string flag position be the position of & in
- # the option string.
- Option = "&"
- Pos = NumOpt
- # Prefix Arg with a char so that ArgInd will point to the
- # first char of the numeric option.
- Arg = "&" Arg
- ArgLen++
- }
- # Find position of flag in option string, to get its type (if any).
- # Disallow & as literal flag.
- else if (!(Pos = index(OptList,Option)) || Option == "&") {
- if (AllowUnrecOpt) {
- Escape = 1
- break
- }
- else {
- OptErr = "Invalid option: " specGiven Option
- return -3
- }
- }
-
- # Find what the value of the option will be if it takes one.
- # NeedNextOpt is true if the option specifier is the last char of
- # this arg, which means that if the option requires a value it is
- # the next arg.
- if (NeedNextOpt = (ArgInd >= ArgLen)) { # Value is the next arg
- if (GotValue = ArgNum + 1 < argc)
- Value = argv[ArgNum+1]
- }
- else { # Value is included with option
- Value = substr(Arg,ArgInd + 1)
- GotValue = 1
- }
-
- if (HadValue = AssignVal(Option,Value,Options,
- substr(OptList,Pos + 1,1),GotValue,"",++OptionNum,!NeedNextOpt,
- specGiven)) {
- if (HadValue < 0) # error occured
- return HadValue
- if (HadValue == 2)
- ArgInd++ # Account for the single-char value we used.
- else {
- if (NeedNextOpt) { # option took next arg as value
- delete argv[++ArgNum]
- ArgsLeft--
- }
- break # This option has been used up
- }
- }
- }
- if (Escape)
- break
- # Do not delete arg until after processing of it, so that if it is not
- # recognized it can be left in ARGV[].
- delete argv[ArgNum]
- ArgsLeft--
- }
- if (compress != 0) {
- dest = 1
- src = argc - ArgsLeft + 1
- for (count = ArgsLeft - 1; count; count--) {
- ARGV[dest] = ARGV[src]
- dest++
- src++
- }
- }
- return ArgsLeft
- }
-
- # Assignment to values in Options[] occurs only in this function.
- # Option: Option specifier character.
- # Value: Value to be assigned to option, if it takes a value.
- # Options[]: Options array to return values in.
- # ArgType: Argument type specifier character.
- # GotValue: Whether any value is available to be assigned to this option.
- # Name: Name of option being processed.
- # OptionNum: Number of this option (starting with 1) if set in argv[],
- # or 0 if it was given in a config file or in the environment.
- # SingleOpt: true if the value (if any) that is available for this option was
- # given as part of the same command line arg as the option. Used only for
- # options from the command line.
- # specGiven is the option specifier character use, if any (e.g. - or +),
- # for use in error messages.
- # Global variables: OptErr
- # Return value: negative value on error, 0 if option did not require an
- # argument, 1 if it did & used the whole arg, 2 if it required just one char of
- # the arg.
- # Current error values:
- # -1: Option that required an argument did not get it.
- # -2: Value of incorrect type supplied for option.
- # -3: Bad type given for option &
- function AssignVal(Option,Value,Options,ArgType,GotValue,Name,OptionNum,
- SingleOpt,specGiven, UsedValue,Err,NumTypes) {
- # If option takes a value... [
- NumTypes = "*()#<>]"
- if (Option == "&" && ArgType !~ "[" NumTypes) { # ]
- OptErr = "Bad type given for & option"
- return -3
- }
-
- if (UsedValue = (ArgType ~ "[:;" NumTypes)) { # ]
- if (!GotValue) {
- if (Name != "")
- OptErr = "Variable requires a value -- " Name
- else
- OptErr = "option requires an argument -- " Option
- return -1
- }
- if ((Err = CheckType(ArgType,Value,Option,Name,specGiven)) != "") {
- OptErr = Err
- return -2
- }
- # Mark this as a numeric variable; will be propogated to Options[] val.
- if (ArgType != ":" && ArgType != ";")
- Value += 0
- if ((Instance = ++Options[Option,"count"]) > 1)
- Options[Option,Instance] = Value
- else
- Options[Option] = Value
- }
- # If this is an environ or rcfile assignment & it was given a value...
- else if (!OptionNum && Value != "") {
- UsedValue = 1
- # If the value is "0" or "-" and this is the first instance of it,
- # do not set Options[Option]; this allows an assignment in an rcfile to
- # turn off an option (for the simple "Option in Options" test) in such
- # a way that it cannot be turned on in a later file.
- if (!(Option in Options) && (Value == "0" || Value == "-"))
- Instance = 1
- else
- Instance = ++Options[Option]
- # Save the value even though this is a flag
- Options[Option,Instance] = Value
- }
- # If this is a command line flag and has a - following it in the same arg,
- # it is being turned off.
- else if (OptionNum && SingleOpt && substr(Value,1,1) == "-") {
- UsedValue = 2
- if (Option in Options)
- Instance = ++Options[Option]
- else
- Instance = 1
- Options[Option,Instance]
- }
- # If this is a flag assignment without a value, increment the count for the
- # flag unless it was turned off. The indicator for a flag being turned off
- # is that the flag index has not been set in Options[] but it has an
- # instance count.
- else if (Option in Options || !((Option,1) in Options))
- # Increment number of times this flag seen; will inc null value to 1
- Instance = ++Options[Option]
- Options[Option,"num",Instance] = OptionNum
- return UsedValue
- }
-
- # Option is the option letter
- # Value is the value being assigned
- # Name is the var name of the option, if any
- # ArgType is one of:
- # : String argument
- # ; Non-null string argument
- # * Floating point argument
- # ( Non-negative floating point argument
- # ) Positive floating point argument
- # # Integer argument
- # < Non-negative integer argument
- # > Positive integer argument
- # specGiven is the option specifier character use, if any (e.g. - or +),
- # for use in error messages.
- # Returns null on success, err string on error
- function CheckType(ArgType,Value,Option,Name,specGiven, Err,ErrStr) {
- if (ArgType == ":")
- return ""
- if (ArgType == ";") {
- if (Value == "")
- Err = "must be a non-empty string"
- }
- # A number begins with optional + or -, and is followed by a string of
- # digits or a decimal with digits before it, after it, or both
- else if (Value !~ /^[-+]?([0-9]+|[0-9]*\.[0-9]+|[0-9]+\.)$/)
- Err = "must be a number"
- else if (ArgType ~ "[#<>]" && Value ~ /\./)
- Err = "may not include a fraction"
- else if (ArgType ~ "[()<>]" && Value < 0)
- Err = "may not be negative"
- # (
- else if (ArgType ~ "[)>]" && Value == 0)
- Err = "must be a positive number"
- if (Err != "") {
- ErrStr = "Bad value \"" Value "\". Value assigned to "
- if (Name != "")
- return ErrStr "variable " substr(Name,1,1) " " Err
- else {
- if (Option == "&")
- Option = Value
- return ErrStr "option " specGiven substr(Option,1,1) " " Err
- }
- }
- else
- return ""
- }
-
- # Note: only the above functions are needed by ProcArgs.
- # The rest of these functions call ProcArgs() and also do other
- # option-processing stuff.
-
- # Opts: Process command line arguments.
- # Opts processes command line arguments using ProcArgs()
- # and checks for errors. If an error occurs, a message is printed
- # and the program is exited.
- #
- # Input variables:
- # Name is the name of the program, for error messages.
- # Usage is a usage message, for error messages.
- # OptList the option description string, as used by ProcArgs().
- # MinArgs is the minimum number of non-option arguments that this
- # program should have, non including ARGV[0] and +h.
- # If the program does not require any non-option arguments,
- # MinArgs should be omitted or given as 0.
- # rcFiles, if given, is a colon-seprated list of filenames to read for
- # variable initialization. If a filename begins with ~/, the ~ is replaced
- # by the value of the environment variable HOME. If a filename begins with
- # $, the part from the character after the $ up until (but not including)
- # the first character not in [a-zA-Z0-9_] will be searched for in the
- # environment; if found its value will be substituted, if not the filename will
- # be discarded.
- # rcfiles are read in the order given.
- # Values given in them will not override values given on the command line,
- # and values given in later files will not override those set in earlier
- # files, because AssignVal() will store each with a different instance index.
- # The first instance of each variable, either on the command line or in an
- # rcfile, will be stored with no instance index, and this is the value
- # normally used by programs that call this function.
- # VarNames is a comma-separated list of variable names to map to options,
- # in the same order as the options are given in OptList.
- # If EnvSearch is given and nonzero, the first EnvSearch variables will also be
- # searched for in the environment. If set to -1, all values will be searched
- # for in the environment. Values given in the environment will override
- # those given in the rcfiles but not those given on the command line.
- # NoRCopt, if given, is an additional letter option that if given on the
- # command line prevents the rcfiles from being read.
- # See ProcArgs() for a description of AllowUnRecOpt and optChars, and
- # ExclusiveOptions() for a description of exOpts.
- # Special options:
- # If x is made an option and is given, some debugging info is output.
- # h is assumed to be the help option.
-
- # Global variables:
- # The command line arguments are taken from ARGV[].
- # The arguments that are option specifiers and values are removed from
- # ARGV[], leaving only ARGV[0] and the non-option arguments.
- # The number of elements in ARGV[] should be in ARGC.
- # After processing, ARGC is set to the number of elements left in ARGV[].
- # The option values are put in Options[].
- # On error, Err is set to a positive integer value so it can be checked for in
- # an END block.
- # Return value: The number of elements left in ARGV is returned.
- # Must keep OptErr global since it may be set by InitOpts().
- function Opts(Name,Usage,OptList,MinArgs,rcFiles,VarNames,EnvSearch,NoRCopt,
- AllowUnrecOpt,optChars,exOpts, ArgsLeft,e) {
- if (MinArgs == "")
- MinArgs = 0
- ArgsLeft = ProcArgs(ARGC,ARGV,OptList NoRCopt,Options,1,AllowUnrecOpt,
- optChars)
- if (ArgsLeft < (MinArgs+1) && !("h" in Options)) {
- if (ArgsLeft >= 0) {
- OptErr = "Not enough arguments"
- Err = 4
- }
- else
- Err = -ArgsLeft
- printf "%s: %s.\nUse -h for help.\n%s\n",
- Name,OptErr,Usage > "/dev/stderr"
- exit 1
- }
- if (rcFiles != "" && (NoRCopt == "" || !(NoRCopt in Options)) &&
- (e = InitOpts(rcFiles,Options,OptList,VarNames,EnvSearch)) < 0)
- {
- print Name ": " OptErr ".\nUse -h for help." > "/dev/stderr"
- Err = -e
- exit 1
- }
- if ((exOpts != "") && ((OptErr = ExclusiveOptions(exOpts,Options)) != ""))
- {
- printf "%s: Error: %s\n",Name,OptErr > "/dev/stderr"
- Err = 1
- exit 1
- }
- return ArgsLeft
- }
-
- # ReadConfFile(): Read a file containing var/value assignments, in the form
- # <variable-name><assignment-char><value>.
- # Whitespace (spaces and tabs) around a variable (leading whitespace on the
- # line and whitespace between the variable name and the assignment character)
- # is stripped. Lines that do not contain an assignment operator or which
- # contain a null variable name are ignored, other than possibly being noted in
- # the return value. If more than one assignment is made to a variable, the
- # first assignment is used.
- # Input variables:
- # File is the file to read.
- # Comment is the line-comment character. If it is found as the first non-
- # whitespace character on a line, the line is ignored.
- # Assign is the assignment string. The first instance of Assign on a line
- # separates the variable name from its value.
- # If StripWhite is true, whitespace around the value (whitespace between the
- # assignment char and trailing whitespace on the line) is stripped.
- # VarPat is a pattern that variable names must match.
- # Example: "^[a-zA-Z][a-zA-Z0-9]+$"
- # If FlagsOK is true, variables are allowed to be "set" by being put alone on
- # a line; no assignment operator is needed. These variables are set in
- # the output array with a null value. Lines containing nothing but
- # whitespace are still ignored.
- # Output variables:
- # Values[] contains the assignments, with the indexes being the variable names
- # and the values being the assigned values.
- # Lines[] contains the line number that each variable occured on. A flag set
- # is record by giving it an index in Lines[] but not in Values[].
- # Return value:
- # If any errors occur, a string consisting of descriptions of the errors
- # separated by newlines is returned. In no case will the string start with a
- # numeric value. If no errors occur, the number of lines read is returned.
- function ReadConfigFile(Values,Lines,File,Comment,Assign,StripWhite,VarPat,
- FlagsOK,
- Line,Status,Errs,AssignLen,LineNum,Var,Val) {
- if (Comment != "")
- Comment = "^" Comment
- AssignLen = length(Assign)
- if (VarPat == "")
- VarPat = "." # null varname not allowed
- while ((Status = (getline Line < File)) == 1) {
- LineNum++
- sub("^[ \t]+","",Line)
- if (Line == "") # blank line
- continue
- if (Comment != "" && Line ~ Comment)
- continue
- if (Pos = index(Line,Assign)) {
- Var = substr(Line,1,Pos-1)
- Val = substr(Line,Pos+AssignLen)
- if (StripWhite) {
- sub("^[ \t]+","",Val)
- sub("[ \t]+$","",Val)
- }
- }
- else {
- Var = Line # If no value, var is entire line
- Val = ""
- }
- if (!FlagsOK && Val == "") {
- Errs = Errs \
- sprintf("\nBad assignment on line %d of file %s: %s",
- LineNum,File,Line)
- continue
- }
- sub("[ \t]+$","",Var)
- if (Var !~ VarPat) {
- Errs = Errs sprintf("\nBad variable name on line %d of file %s: %s",
- LineNum,File,Var)
- continue
- }
- if (!(Var in Lines)) {
- Lines[Var] = LineNum
- if (Pos)
- Values[Var] = Val
- }
- }
- if (Status)
- Errs = Errs "\nCould not read file " File
- close(File)
- return Errs == "" ? LineNum : substr(Errs,2) # Skip first newline
- }
-
- # Variables:
- # Data is stored in Options[].
- # rcFiles, OptList, VarNames, and EnvSearch are as as described for Opts().
- # Global vars:
- # Sets OptErr. Uses ENVIRON[].
- # If anything is read from any of the rcfiles, sets READ_RCFILE to 1.
- function InitOpts(rcFiles,Options,OptList,VarNames,EnvSearch,
- Line,Var,Pos,Vars,Map,CharOpt,NumVars,TypesInd,Types,Type,Ret,i,rcFile,
- fNames,numrcFiles,filesRead,Err,Values,retStr) {
- split("",filesRead,"") # make awk know this is an array
- NumVars = split(VarNames,Vars,",")
- TypesInd = Ret = 0
- if (EnvSearch == -1)
- EnvSearch = NumVars
- for (i = 1; i <= NumVars; i++) {
- Var = Vars[i]
- CharOpt = substr(OptList,++TypesInd,1)
- if (CharOpt ~ "^[:;*()#<>&]$")
- CharOpt = substr(OptList,++TypesInd,1)
- Map[Var] = CharOpt
- Types[Var] = Type = substr(OptList,TypesInd+1,1)
- # Do not overwrite entries from environment
- if (i <= EnvSearch && Var in ENVIRON &&
- (Err = AssignVal(CharOpt,ENVIRON[Var],Options,Type,1,Var,0)) < 0)
- return Err
- }
-
- numrcFiles = split(rcFiles,fNames,":")
- for (i = 1; i <= numrcFiles; i++) {
- rcFile = fNames[i]
- if (rcFile ~ "^~/")
- rcFile = ENVIRON["HOME"] substr(rcFile,2)
- else if (rcFile ~ /^\$/) {
- rcFile = substr(rcFile,2)
- match(rcFile,"^[a-zA-Z0-9_]*")
- envvar = substr(rcFile,1,RLENGTH)
- if (envvar in ENVIRON)
- rcFile = ENVIRON[envvar] substr(rcFile,RLENGTH+1)
- else
- continue
- }
- if (rcFile in filesRead)
- continue
- # rcfiles are liable to be given more than once, e.g. UHOME and HOME
- # may be the same
- filesRead[rcFile]
- if ("x" in Options)
- printf "Reading configuration file %s\n",rcFile > "/dev/stderr"
- retStr = ReadConfigFile(Values,Lines,rcFile,"#","=",0,"",1)
- if (retStr > 0)
- READ_RCFILE = 1
- else if (ret != "") {
- OptErr = retStr
- Ret = -1
- }
- for (Var in Lines)
- if (Var in Map) {
- if ((Err = AssignVal(Map[Var],
- Var in Values ? Values[Var] : "",Options,Types[Var],
- Var in Values,Var,0)) < 0)
- return Err
- }
- else {
- OptErr = sprintf(\
- "Unknown var \"%s\" assigned to on line %d\nof file %s",Var,
- Lines[Var],rcFile)
- Ret = -1
- }
- }
-
- if ("x" in Options)
- for (Var in Map)
- if (Map[Var] in Options)
- printf "(%s) %s=%s\n",Map[Var],Var,Options[Map[Var]] > \
- "/dev/stderr"
- else
- printf "(%s) %s not set\n",Map[Var],Var > "/dev/stderr"
- return Ret
- }
-
- # OptSets is a semicolon-separated list of sets of option sets.
- # Within a list of option sets, the option sets are separated by commas. For
- # each set of sets, if any option in one of the sets is in Options[] AND any
- # option in one of the other sets is in Options[], an error string is returned.
- # If no conflicts are found, nothing is returned.
- # Example: if OptSets = "ab,def,g;i,j", an error will be returned due to
- # the exclusions presented by the first set of sets (ab,def,g) if:
- # (a or b is in Options[]) AND (d, e, or f is in Options[]) OR
- # (a or b is in Options[]) AND (g is in Options) OR
- # (d, e, or f is in Options[]) AND (g is in Options)
- # An error will be returned due to the exclusions presented by the second set
- # of sets (i,j) if: (i is in Options[]) AND (j is in Options[]).
- # todo: make options given on command line unset options given in config file
- # todo: that they conflict with.
- function ExclusiveOptions(OptSets,Options,
- Sets,SetSet,NumSets,Pos1,Pos2,Len,s1,s2,c1,c2,ErrStr,L1,L2,SetSets,NumSetSets,
- SetNum,OSetNum) {
- NumSetSets = split(OptSets,SetSets,";")
- # For each set of sets...
- for (SetSet = 1; SetSet <= NumSetSets; SetSet++) {
- # NumSets is the number of sets in this set of sets.
- NumSets = split(SetSets[SetSet],Sets,",")
- # For each set in a set of sets except the last...
- for (SetNum = 1; SetNum < NumSets; SetNum++) {
- s1 = Sets[SetNum]
- L1 = length(s1)
- for (Pos1 = 1; Pos1 <= L1; Pos1++)
- # If any of the options in this set was given, check whether
- # any of the options in the other sets was given. Only check
- # later sets since earlier sets will have already been checked
- # against this set.
- if ((c1 = substr(s1,Pos1,1)) in Options)
- for (OSetNum = SetNum+1; OSetNum <= NumSets; OSetNum++) {
- s2 = Sets[OSetNum]
- L2 = length(s2)
- for (Pos2 = 1; Pos2 <= L2; Pos2++)
- if ((c2 = substr(s2,Pos2,1)) in Options)
- ErrStr = ErrStr "\n"\
- sprintf("Cannot give both %s and %s options.",
- c1,c2)
- }
- }
- }
- if (ErrStr != "")
- return substr(ErrStr,2)
- return ""
- }
-
- # The value of each instance of option Opt that occurs in Options[] is made an
- # index of Set[].
- # The return value is the number of instances of Opt in Options.
- function Opt2Set(Options,Opt,Set, count) {
- if (!(Opt in Options))
- return 0
- Set[Options[Opt]]
- count = Options[Opt,"count"]
- for (; count > 1; count--)
- Set[Options[Opt,count]]
- return count
- }
-
- # The value of each instance of option Opt that occurs in Options[] that
- # begins with "!" is made an index of nSet[] (with the ! stripped from it).
- # Other values are made indexes of Set[].
- # The return value is the number of instances of Opt in Options.
- function Opt2Sets(Options,Opt,Set,nSet, count,aSet,ret) {
- ret = Opt2Set(Options,Opt,aSet)
- for (value in aSet)
- if (substr(value,1,1) == "!")
- nSet[substr(value,2)]
- else
- Set[value]
- return ret
- }
-
- # Returns true if option Opt was given on the command line.
- function CmdLineOpt(Options,Opt, i) {
- for (i = 1; (Opt,"num",i) in Options; i++)
- if (Options[Opt,"num",i] != 0)
- return 1
- return 0
- }
- ### End of ProcArgs library
-