#!/usr/local/bin/gawk -f #!/usr/bin/awk -f # @(#) name.gawk 2.3 97/06/11 # 90/06/01 john h. dubois iii (john@armory.com) # 90/11/14 removed ksh-specific code # 91/06/30 removed dependency on having variable assignments given # on awk command line set before execution of BEGIN block # (doesn't work in some awks) # 91/12/07 added PATH setting, # added code to get rid of phone number in GCOS field # 92/05/02 converted to #!awk script # 96/06/18 Added all options. # 96/06/23 Added g option. # 96/09/10 2.0: Use pwent library. Added ec options. # 96/11/17 Let UIDs be given. Added x option. # 96/12/17 Added rsGanC options, config file, and home dir search. # 97/01/07 Added P option. BEGIN { Name = "name" Usage = "Usage: " Name " [-ahgecCprsGn] ..." rcFile = "." Name "rc" ARGC = Opts(Name,Usage,"apPecCgxrsGh",1,"~/" rcFile ":$UHOME/" rcFile, "AUTOGCOS,ALLFIELDS,VERBOSE,EXACT,CASE,AUTOCASE",0,"n",0,"","g,s,G;p,P") if ("h" in Options) { printf \ "%s: Print users' real names from /etc/passwd.\n"\ "%s\n"\ "The \"real name\" (the GCOS field from /etc/passwd) for each named user is\n"\ "printed, in the format\n"\ "userreal-name\n"\ "If a user name consists entirely of digits and no options (except -p) are\n"\ "given, the name is taken to be a UID to search for.\n"\ "If a user name contains any '/' characters and no options (except -p) are\n"\ "given, the name is taken to be a home directory to search for.\n"\ "Options:\n"\ "Some of the following options can also be set by putting variables in a\n"\ "configuration file named %s. This file is searched for first in the home\n"\ "directory of the invoking user and then, if the environment variable UHOME\n"\ "is set, in the directory specified by that variable. If both files exist,\n"\ "variables assignments in the first file override those in the second file.\n"\ "Variables are set by putting the indicated variable name in the file. To\n"\ "turn off a flag option in the first file and prevent it from being set in\n"\ "the second file, assign it a value of 0. e.g. if FOO is set in the first\n"\ "file, FOO=0 in the second file will override it. Options can be turned\n"\ "off on the command line by following them immediately with \"-\", e.g. -v-\n"\ "to turn off the v option in such a way that it cannot be turned on in a\n"\ "config file. Variable names appear in parentheses in the option\n"\ "descriptions.\n"\ "-h: Print this help.\n"\ "-g: Search for names in the GCOS (\"real name\") field instead of the\n"\ " account name field. The search is not case sensitive. Unlike\n"\ " searches by account name, the name need not match the entire field.\n"\ " The words of each name given must occur in the same order in a GCOS\n"\ " field in order for a match to occur. Multiple password file entries\n"\ " may be matched by one name. If multiple words of a name are given,\n"\ " they must be quoted to form a single argument. Example:\n"\ " %s -g 'john somebody'\n"\ "-r: Treat the given names as unanchored regular expressions. Names are\n"\ " compared to the same field that would be searched without -r. With\n"\ " this option, the meaning of -e is changed to mean that the regular\n"\ " expression should be anchored at the start and end, and the meaning\n"\ " of -c is changed to mean that the match should be case sensitive.\n"\ "-a: If a name is not found as a user name, search for it in the GCOS field\n"\ " as though -g had been given. (AUTOGCOS)\n"\ "-e: An exact match of the full GCOS field is required. (EXACT)\n"\ "-c: Matches against the GCOS field are made case sensitive. (CASE)\n"\ "-C: Like -c, except that a match is only case sensitive for names that\n"\ " are given with some characters in upper case. (AUTOCASE)\n"\ "If -e, -c, or -C is given on the command line and -r is not given, the -g\n"\ "option is turned on. If the e, c, or C option is turn on by puttings its\n"\ "variable in a config file, they only have an effect if -r or -g is given.\n"\ "-s: Take the command line arguments to be the names of login shells, and\n"\ " print users who have any of the shells.\n"\ "-G: Take the command line arguments to be the names or numeric IDs of\n"\ " groups, and print users who have any of them as their login group.\n"\ "-n: Do not read the configuration file.\n"\ "-p: Print entire password database lines for each user. (ALLFIELDS)\n"\ "-P: Print all password database fields (except the password) for each user\n"\ " in a more readable format, with headers. Fields may be truncated so\n"\ " that each record fits on an 80-character line. (VERBOSE)\n", Name,Usage,Name,Name exit(0) } Debug = "x" in Options Verbose = "P" in Options WholePasswd = "p" in Options autoGCOS = "a" in Options CaseSensitive = "c" in Options Full = "e" in Options regex = "r" in Options autoCase = "C" in Options GCOS = ("g" in Options) || !regex && (CmdLineOpt(Options,"e") || \ CmdLineOpt(Options,"C") || CmdLineOpt(Options,"c")) ReadPasswd() # Set PW_ values if ("s" in Options) fieldReq = PW_SHELL else if (GCOS) fieldReq = PW_GCOS else if ("G" in Options) { fieldReq = PW_GID getGroupMap(gMap) for (i = 1; i < ARGC; i++) if ((user = ARGV[i]) !~ /^[0-9]+$/) if (user in gMap) ARGV[i] = gMap[user] else { errCt++ printf "%s: No group with this name: %s\n",Name, user > "/dev/stderr" delete ARGV[i] } if (errCt == ARGC-1) exit 1 } for (argnum = 1; argnum < ARGC; argnum++) { if (!(argnum in ARGV)) continue user = ARGV[argnum] if (fieldReq) Field = fieldReq else if (user ~ /^[0-9]+$/) Field = PW_UID else if (user ~ "/") Field = PW_HOME else Field = PW_NAME if (Debug) printf "%s: Searching for user: %s\n",Name,user > "/dev/stderr" if (PWSearch(\ user,Field,Entries,autoGCOS,!CaseSensitive,autoCase,regex,Full)) { if (Debug) printf "%d entries returned by PWSearch().\n", NumElem(Entries) > "/dev/stderr" for (i = 1; i in Entries; i++) printEntry(Entries[i],WholePasswd,Verbose) } else printf "%s: No user with this %s: %s\n",Name, (Field == PW_NAME && autoGCOS) ? \ pwFieldNames[PW_NAME] " or " pwFieldNames[PW_GCOS] : \ pwFieldNames[Field],user > "/dev/stderr" } exit 0 } # PWSearch: find entries in password file that match given criteria. # pat: Fixed string or pattern to compare to a password field. # Field: which password field to compare pat to, from the PW_* set. # Entries[]: The indexes of matching entries in the password database are # returned as values in Entries[]. The index for each value in an # integer giving the order in which it was found (starting with 1). # autoGCOS: If Field is PW_NAME and autoGCOS is true, pat is first searched # for in the name field; if it is not found there, it is searched for in # the "real name" field (part of the GCOS field). # ignoreCase: make matches be independent of case. # autoCase: If ignoreCase is false and autoCase is true, then matches are case # case independent only if there are no upper case letters in pat. # regex: pat is treated as a regular expression and compared to the "real name" # field. # Full: If regex is true, it is required to match the entire "real name" field. # Globals: Debug, pwFieldNames, PW_* # Return value: number of matching entries found (the highest index in # Entries[]). function PWSearch(pat,Field,Entries,autoGCOS,ignoreCase,autoCase,regex,Full, oIC,PWEnt,num) { split("",Entries) # empty if (ignoreCase && autoCase) ignoreCase = (pat !~ /[A-Z]/) num = 0 if (Field == PW_NAME && autoGCOS) if (num = PWSearch(pat,Field,Entries,0,ignoreCase,0,regex,Full)) return num else { Field = PW_GCOS if (Debug) printf "No match for '%s' in name field, trying GCOS...\n", pat > "/dev/stderr" } if (Debug) printf "Searching for %s in \"%s\" field\n", pat,pwFieldNames[Field] > "/dev/stderr" if (regex) { oIC = IGNORECASE IGNORECASE = ignoreCase if (Full) pat = "^(" pat ")$" setpwent() while (getpwent(PWEnt,0,PW_REAL) != ":") if (PWEnt[Field] ~ pat) Entries[++num] = PWEnt[PW_RECORD] IGNORECASE = oIC } else { if (!getpw(Field,pat,PWEnt,"",0,ignoreCase,Full)) return 0 Entries[++num] = PWEnt[PW_RECORD] while (getpw(Field,pat,PWEnt,"",1,ignoreCase,Full)) Entries[++num] = PWEnt[PW_RECORD] } if (Debug) printf "Got %d match(es).\n",num > "/dev/stderr" return num } function trunc(s,len) { if (length(s) > len) s = substr(s,1,len-1) ">" return s } # Globals: HeaderPrinted, PW_* function printEntry(i,WholePasswd,Verbose, Format,Name,Home,Shell,PWEnt,line) { line = PWLines[i] if (WholePasswd) print line else { PWGetFields(line,PWEnt,PW_REAL) if (Verbose) { Format = "%-8s %5s %5s %-28s %-12s %s\n" if (!HeaderPrinted) { printf Format,"User","UID","LGID", "Name Office","Home dir","Login shell" HeaderPrinted = 1 } # Let name overflow into office field Name = PWEnt[PW_REAL] if (PWEnt[PW_OFFICE] != "") Name = sprintf("%-15s %s",Name,PWEnt[PW_OFFICE]) printf Format,PWEnt[PW_NAME],PWEnt[PW_UID],PWEnt[PW_GID], trunc(Name,28),trunc(PWEnt[PW_HOME],12),trunc(PWEnt[PW_SHELL],15) } else printf "%s\t%s\n",PWEnt[PW_NAME],PWEnt[PW_REAL] } } # Globals: FS, $* function getGroupMap(map, ret,count,ofs) { ofs = FS FS = ":" while ((ret = (getline < "/etc/group")) == 1) { map[$1] = $3 count++ } close("/etc/group") FS = ofs return ret ? -1 : count } ### Begin pwent library # @(#) pwent.awk 1.3 96/12/15 # 92/08/10 john h. dubois III (john@armory.com) # 93/12/13 fixed to not clobber $* # 96/01/05 Send error messages to /dev/stderr # 96/05/24 Let getpwnam() return a specific field if requested. # Added PW_REAL and PW_OFFICE. # 96/06/03 Added Type field to getpwent() # 96/06/24 Allow a Field to be requested for getpwent() also. # 96/06/29 Added PW_RECORD, and getpwreal(). # Changed PWLines to be index by record number instead of name. # 96/11/17 Added getpwuid() # 96/12/15 Added pwFieldNames, and pwent() as general select-by-field routine. # Require: ReadShells() # getpwent, getpwnam: get an entry from the passwd file. # Each of the following passwd functions returns an array which contains # a passwd file entry. The array contains the fields of the entry. # Global variables: # The following variables are defined with the values of the indexes of the # entries: PW_NAME, PW_PASSWORD, PW_UID, PW_GID, PW_GCOS, PW_HOME, PW_SHELL # PWLines[] contains the lines of the password file, indexed by record number, # starting with 1. # _pwNames[] is a mapping of name to passwd record number. # pwFieldNames[field-index] is set to a short description of each field. # getpwentNum is the number of the next entry to be returned by getpwent(). # Left FS global because making it local does not work in gawk. function ReadPasswd( User,Line,i,Ind,ret) { if (PW_Name) return 1 PW_NAME = 1 PW_PASSWORD = 2 PW_UID = 3 PW_GID = 4 PW_GCOS = 5 PW_HOME = 6 PW_SHELL = 7 PW_REAL = -1 # for PWGetFields() PW_OFFICE = -2 PW_RECORD = -3 split(\ "user name,password,UID,login GID,real name,home directory,login shell", pwFieldNames,",") getpwentNum = 1 while ((ret = (getline Line < "/etc/passwd")) == 1) { PWLines[++Ind] = Line _pwNames[substr(Line,1,index(Line,":")-1)] = Ind } _num_pw = Ind close("/etc/passwd") if (ret) { printf "ReadPasswd(): Could not open /etc/passwd: %s\n", ERRNO > "/dev/stderr" return 0 } return 1 } # setpwent resets the passwd file entry pointer used by getpwent # to the first entry. function setpwent() { getpwentNum = 1 } # getpwent sets PWEnt to the next entry in the passwd file. # If Type is set to -1, the entry for the next "real" user is returned (others # are skipped over), where a real user is a user whose login shell is listed in # /etc/shells. This requires the ReadShells() function. Other values for # Type are not yet defined and are ignored. # If the last entry has already been returned, 0 is return if Field is null, # ":" if not. # If the entry for the next real user has been requested and /etc/shells # cannot be read, -1 is returned if Field is null, "\n" if not. # See PWGetFields() for other return values and the meaning of the Field # parameter. function getpwent(PWEnt,Type,Field, entNum) { if (!PW_NAME) ReadPasswd() if (!(getpwentNum in PWLines)) return Field ? ":" : 0 if (Type == -1) { if (!_DidReadShells && ReadShells(LoginShells) == -1) return Field ? "\n" : -1 split(PWLines[getpwentNum++],PWEnt,":") while (!(PWEnt[PW_SHELL] in LoginShells)) { if (!(getpwentNum in PWLines)) return Field ? ":" : 0 split(PWLines[getpwentNum++],PWEnt,":") } return PWGetFields("",PWEnt,Field,getpwentNum - 1) } else { entNum = getpwentNum return PWGetFields(PWLines[getpwentNum++],PWEnt,Field,entNum) } } # PWGetFields() splits PWLine into PWEnt[], and optionally returns a field # from it. If PWLine is null, PWEnt[] is assumed to have already been filled # in with a password entry. # If Field is not passed or is null, the return value is 1. # If Field is non-null, it should a PW_ value. In this case, the value of the # requested field is returned. # If entNum is nonzero, it is the value that PWEnt[PW_RECORD] should be set to. # It should be the index in PWLines[] of the record being processed. # In addition to the PW_ values used by the rest of the functions in this # library, this function can be passed PW_REAL and PW_OFFICE. # PW_REAL will get the part of the GCOS field before the first comma. # PW_OFFICE will get the part of the GCOS field after the first comma. # If either of these is requested, both values will also be assigned to their # indices in PWEnt[], unless there is no comma in the GCOS field, in which case # PW_OFFICE will not be set. # NOTE: since the global field names are set in ReadShells(), it must be # executed before any of the field name can be passed. function PWGetFields(PWLine,PWEnt,Field,entNum, gcos,ind) { if (PWLine != "") split(PWLine,PWEnt,":") if (entNum) PWEnt[PW_RECORD] = entNum if (!Field) return 1 if (Field < 0) { if (ind = index(gcos = PWEnt[PW_GCOS],",")) { PWEnt[PW_OFFICE] = substr(gcos,ind+1) PWEnt[PW_REAL] = substr(gcos,1,ind-1) } else PWEnt[PW_REAL] = gcos } return PWEnt[Field] } # getpwnam sets PWEnt to the passwd entry for login name Name. # If Next is true or Name does not exist in the password file, the return value # is ":" if Field was passed, 0 if not. # For other return values and parameter explanation, see PWGetFields() function getpwnam(Name,PWEnt,Field,Next) { if (!PW_NAME) ReadPasswd() if (!Next && Name in _pwNames) return PWGetFields(PWLines[_pwNames[Name]],PWEnt,Field,_pwNames[Name]) else return Field ? ":" : 0 } # Build uid->pw-index and home->pw-index # Globals: _pwIndexes[] function MakeInd( Elem,Ind,Line,i,Fields,f) { Fields[PW_UID] Fields[PW_HOME] Fields[PW_GID] Fields[PW_SHELL] for (Ind = 1; Ind in PWLines; Ind++) { Line = PWLines[Ind] split(Line,Elem,":") for (f in Fields) { i = f ":" Elem[f] if (i in _pwIndexes) _pwIndexes[i] = _pwIndexes[i] "," Ind else _pwIndexes[i] = Ind } } IndDone = 1 } # getpw sets PWEnt to the first passwd entry whose FieldNum'th field is equal # to Value. FieldNum may select any field except the password field. # If Next is true, Value is ignored and the next entry in the password file # that has the same FieldNum field as the last one requested is returned. # See getpwnam() for return values and the meaning of the Field param. # IgnoreCase and Full are used only for PW_GCOS searches; see getpwreal() # for their meaning. # Uses globals _pwMatches[] to track matches between calls. function getpw(FieldNum,Value,PWEnt,Field,Next,IgnoreCase,Full, elem,i,n) { if (FieldNum == PW_GCOS) return getpwreal(Value,PWEnt,Field,Next,IgnoreCase,Full) if (FieldNum == PW_NAME) return getpwnam(Value,PWEnt,Field,Next) if (Next) { if ((FieldNum,_pwMatches[FieldNum,"cur"]) in _pwMatches) { i = _pwMatches[FieldNum,_pwMatches[FieldNum,"cur"]++] return PWGetFields(PWLines[i],PWEnt,Field,i) } } else { if (!IndDone) MakeInd() Value = FieldNum ":" Value if (Value in _pwIndexes) { n = split(_pwIndexes[Value],elem,",") for (i = 1; i <= n; i++) _pwMatches[FieldNum,i] = elem[i] delete _pwMatches[FieldNum,n+1] # so we know when to end _pwMatches[FieldNum,"cur"] = 2 return PWGetFields(PWLines[elem[1]],PWEnt,Field,elem[1]) } } return Field ? ":" : 0 } function getpwhome(home,PWEnt,Field,Next) { if (!PW_NAME) # set PW_ values ReadPasswd() return getpw(PW_HOME,home,PWEnt,Field,Next) } function getpwuid(UID,PWEnt,Field,Next) { if (!PW_NAME) # set PW_ values ReadPasswd() return getpw(PW_UID,(UID+0),PWEnt,Field,Next) } # Make an index by real name. For each passwd file entry, the real-name # is lowercased and split into components on non-alphanums. The passwd entry # index that the name came from is added to the value of each such component # in the global _RealInd[]. The indexes stored this way are separated by # commas. If the real-name contains no alphanums, its index is stored under # the null index. function _makeRealInd( PWEnt,ret,Elem,nelem,i,Component) { setpwent() while ((ret = getpwent(PWEnt,"",PW_REAL)) != ":") { nelem = split(tolower(ret),Elem,/[^a-z0-9]+/) for (i = 1; i <= nelem; i++) { Component = Elem[i] if (Component == "" && nelem > 1) continue if (Component in _RealInd) _RealInd[Component] = _RealInd[Component] "," PWEnt[PW_RECORD] else _RealInd[Component] = PWEnt[PW_RECORD] } } _realIndDone = 1 } # Make Name into a pattern that will match a name that contains all of the # same name components (sequences of alphanums) in the same order. If Name # contains no name components, a null string is returned. function MakeNamePat(Name, Elem,nelem,i,Pat,e) { nelem = split(Name,Elem,/[^a-zA-Z0-9]+/) for (i = 1; i <= nelem; i++) { if ((e = Elem[i]) == "") continue if (Pat == "") Pat = "(^|[^a-zA-Z0-9])" e else Pat = Pat "[^a-zA-Z0-9](.*[^a-zA-Z0-9])?" e } if (Pat == "") # If Name contained no alphanums... return "" Pat = Pat "([^a-zA-Z0-9]|$)" return Pat } # getpwgreal sets PWEnt to the first passwd entry whose PW_REAL (see # PWGetFields()) field matches Real. Matching occurs if the alphanumeric # components of Real occur in the same order in the entry. Non-alphanums are # ignored. All of the components in Real must occur in the entry, but not all # of the components in the entry must occur in Real. # If the given name does not exist in the password file, # the return value is ":" if Field was passed, 0 if not. # If Next is true, getpwreal() sets PWEnt to the next passwd entry whose # PW_REAL field matches the last previous Real parameter passed. # In this case, if the last entry has already been returned, # the return value is ":" if Field was passed, 0 if not. # Different IgnoreCase and Full parameters may be given when doing a Next # search. Both must always be passed; they do not default to the original # values when doing a Next search. The only parameter ignored when doing a # Next search is Real. # If IgnoreCase is true, case is ignored when searching. # If Full is true, a match of the full name is required (including any # punctuation). # For successful return values and Field parameter explanation, # see PWGetFields() # Globals: For the Next search, between invokations these varies store values: # _getpwrealInd[]: The set of pw indices that matched the query. # _getpwrealIndInd: The next index in _getpwrealInd[] to look at. # _getpwrealReal: The Real value passed with the original query. # _getpwrealPat: Real converted to a component order search pattern. function getpwreal(Real,PWEnt,Field,Next,IgnoreCase,Full, ind,name,Pat) { if (!Next) { if (!PW_NAME) ReadPasswd() if (!_realIndDone) _makeRealInd() _getpwrealReal = Real _getpwrealPat = MakeNamePat(Real) # Get first component from Real Real = tolower(Real) gsub("^[^a-z0-9]+","",Real) gsub("[^a-z0-9].*","",Real) if (!(Real in _RealInd)) return Field ? ":" : 0 split(_RealInd[Real],_getpwrealInd,",") _getpwrealIndInd = 1 } if (Full) Pat = _getpwrealReal else Pat = _getpwrealPat if (IgnoreCase) Pat = tolower(Pat) while (_getpwrealIndInd in _getpwrealInd) { ind = _getpwrealInd[_getpwrealIndInd++] name = PWGetFields(PWLines[ind],PWEnt,PW_REAL,ind) if (IgnoreCase) name = tolower(name) if (Full ? (name == Pat) : (name ~ Pat)) return PWGetFields("",PWEnt,Field,ind) } return Field ? ":" : 0 } ### End pwent library ### 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. # 94/09/23 Fixed bug that caused fail if -opt given as last arg. # 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() # 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 bug 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 # . # 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 ### Begin set library # 96/05/23 added return values jhdiii # 96/05/25 added set2list() # 97/01/26 Added AOnly(), Exclusive() # Return value: the number of new elements added to Inter function Intersection(A,B,Inter, Elem,Count) { for (Elem in A) if (Elem in B && !(Elem in Inter)) { Inter[Elem] Count++ } return Count } # Any element that is in A or B but not both and which is not already in # Excl is added to Excl. # Return value: the number of new elements added to Excl function Exclusive(A,B,Excl) { return AOnly(A,B,Excl) + AOnly(B,A,Excl) } # Any element that is in A and not in B or aOnly is added to aOnly. # Return value: the number of new elements added to aOnly. function AOnly(A,B,aOnly, Elem,Count) { for (Elem in A) if (!(Elem in B) && !(Elem in aOnly)) { aOnly[Elem] Count++ } return Count } # Return value: the number of new elements added to Both function Union(A,B,Both) { return CopySet(A,Both) + CopySet(B,Both) } # Deletes any elements that are in both Minuend and Subtrahend from Minuend. # Return value: the number of elements deleted. function SubtractSet(Minuend,Subtrahend, Elem,nDel) { for (Elem in Subtrahend) if (Elem in Minuend) { delete Minuend[Elem] nDel++ } return nDel } # Return value: the number of new elements added to To function CopySet(From,To, Elem,n) { for (Elem in From) if (!(Elem in To)) { To[Elem] n++ } return n } # Returns 1 if Set is empty, 0 if not. function IsEmpty(Set, i) { for (i in Set) return 0 return 1 } # MakeSet: make a set from a list. # An index with the name of each element of the list is created in the given # array. # Input variables: # Elements is a string containing the list of elements. # Sep is the character that separates the elements of the list. # Output variables: # Set is the array. # Return value: the number of new elements added to the set. function MakeSet(Set,Elements,Sep, i,Num,Names,nFound,ind) { nFound = 0 Num = split(Elements,Names,Sep) for (i = 1; i <= Num; i++) { ind = Names[i] if (!(ind in Set)) { Set[ind] nFound++ } } return nFound } # Returns the number of elements in set Set function NumElem(Set, elem,Num) { for (elem in Set) Num++ return Num } # Remove all elements from Set function DeleteAll(Set, i) { split("",Set,",") } # Returns a list of all of the elements in Set[], with each pair of elements # separated by Sep. function set2list(Set,Sep, list,elem) { for (elem in Set) list = list Sep elem return substr(list,2) # skip 1st separator } ### End set library