.\" This file is part of wordsplit -*- nroff -*- .\" Copyright (C) 2009-2019 Sergey Poznyakoff .\" .\" Wordsplit is free software; you can redistribute it and/or modify .\" it under the terms of the GNU General Public License as published by .\" the Free Software Foundation; either version 3, or (at your option) .\" any later version. .\" .\" Wordsplit is distributed in the hope that it will be useful, .\" but WITHOUT ANY WARRANTY; without even the implied warranty of .\" MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the .\" GNU General Public License for more details. .\" .\" You should have received a copy of the GNU General Public License .\" along with wordsplit. If not, see . .\" .TH WORDSPLIT 3 "July 9, 2019" "WORDSPLIT" "Wordsplit User Reference" .SH NAME wordsplit \- split string into words .SH SYNOPSIS .B #include .sp \fBint wordsplit (const char *\fIs\fB,\ wordsplit_t *\fIws\fB, int \fIflags\fB);\fR .sp \fBint wordsplit_len (const char *\fIs\fB,\ \fBsize_t \fIlen\fR,\ \fBwordsplit_t *\fIp\fB,\ int \fIflags\fB); .sp \fBvoid wordsplit_free (wordsplit_t *\fIp\fB);\fR .sp \fBvoid wordsplit_free_words (wordsplit_t *\fIws\fB);\fR .sp \fBvoid wordsplit_getwords (wordsplit_t *\fIws\fB,\ int *\fIwordc\fB, char ***\fIwordv\fB); .sp \fBvoid wordsplit_perror (wordsplit_t *\fIws\fB);\fR .sp \fBconst char *wordsplit_strerror (wordsplit_t *\fIws\fB);\fR .sp \fBvoid wordsplit_clearerr (wordsplit_t *\fIws\fB);\fR .SH DESCRIPTION The function \fBwordsplit\fR splits the string \fIs\fR into words using a set of rules governed by \fIflags\fR. Depending on \fIflags\fR, the function performs the following operations: whitespace trimming, tilde expansion, variable expansion, quote removal, command substitution, and path expansion. On success, \fBwordsplit\fR returns 0 and stores the words found in the member \fBws_wordv\fR and the number of words in the member \fBws_wordc\fR. On error, a non-zero error code is returned. .PP The function \fBwordsplit_len\fR acts similarly, except that it accesses only first \fBlen\fR bytes of the string \fIs\fR, which is not required to be null-terminated. .PP When no longer needed, the resources allocated by a call to one of these functions must be freed using .BR wordsplit_free . .PP The function .B wordsplit_free_words frees only the memory allocated for elements of .I ws_wordv after which it resets .I ws_wordv to .B NULL and .I ws_wordc to zero. .PP The usual calling sequence is: .PP .EX wordsplit_t ws; int rc; if (wordsplit(s, &ws, WRDSF_DEFFLAGS)) { for (i = 0; i < ws.ws_wordc; i++) { /* do something with ws.ws_wordv[i] */ } } wordsplit_free(&ws); .EE .PP Notice, that \fBwordsplit_free\fR must be called after each invocation of \fBwordsplit\fR or \fBwordsplit_len\fR, even if it resulted in error. .PP The function .B wordsplit_getwords returns in \fIwordv\fR an array of words, and in \fIwordc\fR the number of elements in \fIwordv\fR. The array can be used after calling .BR wordsplit_free . The caller becomes responsible for freeing the memory allocated for each element of the array and the array pointer itself. .PP The function .B wordsplit_perror prints error message from the last invocation of \fBwordsplit\fR. It uses the function pointed to by the .I ws_error member. By default, it outputs the message on the standard error. .PP For more sophisticated error reporting, the function .B wordsplit_strerror can be used. It returns a pointer to the string describing the error. The caller should treat this pointer as a constant string. It should not try to alter or deallocate it. .PP The function .B wordsplit_clearerr clears the error condition associated with \fIws\fR. .SH INCREMENTAL MODE In incremental mode \fBwordsplit\fR parses one word per invocation. It returns \fBWRDSF_OK\fR on success and \fBWRDSF_NOINPUT\fR when entire input string has been processed. .PP This mode is enabled if the flag \fBWRDSF_INCREMENTAL\fR is set in the \fIflags\fR argument. Subsequent calls to \fBwordsplit\fR must have \fBNULL\fR as first argument. Each successful call will return exactly one word in \fBws.ws_wordv[0]\fR. .PP An example usage: .PP .EX wordsplit_t ws; int rc; flags = WRDSF_DEFFLAGS|WRDSF_INCREMENTAL; for (rc = wordsplit(s, &ws, flags); rc == WRDSF_OK; rc = wordsplit(NULL, &ws, flags)) { process(ws.ws_wordv[0]); } if (rc != WRDSE_NOINPUT) wordsplit_perror(&ws); wordsplit_free(&ws); .EE .SH OPTIONS The number of flags is limited to 32 (the width of \fBuint32_t\fR data type). By the time of this writing each bit is already occupied by a corresponding flag. However, the number of features \fBwordsplit\fR provides requires still more. Additional features can be requested by setting a corresponding \fIoption bit\fR in the \fBws_option\fR field of the \fBstruct wordsplit\fR argument. To inform wordsplit functions that this field is initialized the \fBWRDSF_OPTIONS\fR flag must be set. .PP Option symbolic names begin with \fBWRDSO_\fR. They are discussed in detail in the subsequent chapters. .SH EXPANSION Expansion is performed on the input after it has been split into words. The kinds of expansion to be performed are controlled by the appropriate bits set in the \fIflags\fR argument. Whatever expansion kinds are enabled, they are always run in the order described in this section. .SS Whitespace trimming Whitespace trimming removes any leading and trailing whitespace from the initial word array. It is enabled by the .B WRDSF_WS flag. Whitespace trimming is enabled automatically if the word delimiters (\fIws_delim\fR member) contain whitespace characters (\fB\(dq \\t\\n\(dq\fR), which is the default. .SS Variable expansion Variable expansion replaces each occurrence of .BI $ NAME or .BI ${ NAME } with the value of the variable \fINAME\fR. It is enabled by default and can be disabled by setting the \fBWRDSF_NOVAR\fR flag. The caller is responsible for supplying the table of available variables. Two mechanisms are provided: environment array and a callback function. .PP Environment array is a \fBNULL\fR-terminated array of variables, stored in the \fIws_env\fR member. The \fBWRDSF_ENV\fR flag must be set in order to instruct \fBwordsplit\fR to use this array. .PP By default, elements of the \fIws_env\fR array have the form .IR NAME = VALUE . An alternative format is enabled by the .B WRDSF_ENV_KV flag. When it is set, each variable is described by two consecutive elements in the array: .IR ws_env [ n ] containing the variable name, and .IR ws_env [ "n+1" ] containing its value. If the latter is \fBNULL\fR, the corresponding variable is undefined. .PP More sophisticated variable tables can be implemented using callback function. The \fIws_getvar\fR member should be set to point to that function and \fBWRDSF_GETVAR\fR flag must be set. The function itself shall be defined as .PP .EX int getvar (char **ret, const char *var, size_t len, void *clos); .EE .PP The function shall look up the variable identified by the first \fIlen\fR bytes of the string \fIvar\fR. If the variable is found, the function shall store a copy of its value (allocated using \fBmalloc\fR(3)) in the memory location pointed to by \fBret\fR, and return \fBWRDSE_OK\fR. If the variable is not found, the function shall return \fBWRDSE_UNDEF\fR. Otherwise, a non-zero error code shall be returned. .PP If \fIws_getvar\fR returns .BR WRDSE_USERERR , it must store the pointer to the error description string in .BR *ret . In any case (whether returning \fB0\fR or \fBWRDSE_USERERR\fR), the data returned in \fBret\fR must be allocated using .BR malloc (3). .PP If both .I ws_env and .I ws_getvar are used, the variable is first looked up in .IR ws_env . If it is not found there, the .I ws_getvar callback is invoked. This order is reverted if the \fBWRDSO_GETVARPREF\fR option is set. .PP During variable expansion, the forms below cause .B wordsplit to test for a variable that is unset or null. Omitting the colon results in a test only for a variable that is unset. .TP .BI ${ variable :- word } .BR "Use Default Values" . If \fIvariable\fR is unset or null, the expansion of \fIword\fR is substituted. Otherwise, the value of \fIvariable\fR is substituted. .TP .BI ${ variable := word } .BR "Assign Default Values" . If \fIvariable\fR is unset or null, the expansion of \fIword\fR is assigned to \fIvariable\fR. The value of \fIvariable\fR is then substituted. .TP .BI ${ variable :? word } .BR "Display Error if Null or Unset" . If \fIvariable\fR is null or unset, the expansion of \fIword\fR (or a message to that effect if word is not present) is output using .IR ws_error . Otherwise, the value of \fIvariable\fR is substituted. .TP .BI ${ variable :+ word } .BR "Use Alternate Value" . If \fIvariable\fR is null or unset, nothing is substituted, otherwise the expansion of \fIword\fR is substituted. .PP Unless the above forms are used, a reference to an undefined variable expands to empty string. Three flags affect this behavior. If the \fBWRDSF_UNDEF\fR flag is set, expanding undefined variable triggers a \fBWRDSE_UNDEF\fR error. If the \fBWRDSF_WARNUNDEF\fR flag is set, a non-fatal warning is emitted for each undefined variable. Finally, if the \fBWRDSF_KEEPUNDEF\fR flag is set, references to undefined variables are left unexpanded. .PP If two or three of these flags are set simultaneously, the behavior is undefined. .SS Positional argument expansion \fIPositional arguments\fR are special parameters that can be referenced in the input string by their ordinal number. The numbering begins at \fB0\fR. The syntax for referencing positional arguments is the same as for the variables, except that argument index is used instead of the variable name. If the index is between 0 and 9, the \fB$\fIN\fR form is acceptable. Otherwise, the index must be enclosed in curly braces: \fB${\fIN\fB}\fR. .PP During argument expansion, references to positional arguments are replaced with the corresponding values. .PP Argument expansion is requested by the \fBWRDSO_PARAMV\fR option bit. The NULL-terminated array of variables shall be supplied in the .I ws_paramv member. The .I ws_paramc member shall be initialized to the number of elements in .IR ws_paramv . .PP Setting the \fBWRDSO_PARAM_NEGIDX\fR option together with \fBWRDSO_PARAMV\fR enables negative positional argument references. A negative reference has the form \fB${-\fIN\fB}\fR. It is expanded to the value of the argument with index \fB\fIws_paramc\fR \- \fIN\fR. .SS Quote removal During quote removal, single or double quotes surrounding a sequence of characters are removed and the sequence itself is treated as a single word. Characters within single quotes are treated verbatim. Characters within double quotes undergo variable expansion and backslash interpretation (see below). .PP Recognition of single quoted strings is enabled by the \fBWRDSF_SQUOTE\fR flag. Recognition of double quotes is enabled by the \fBWRDSF_DQUOTE\fR flag. The macro \fBWRDSF_QUOTE\fR enables both. .SS Backslash interpretation Backslash interpretation translates unquoted .I escape sequences into corresponding characters. An escape sequence is a backslash followed by one or more characters. By default, each sequence \fB\\\fIC\fR appearing in unquoted words is replaced with the character \fIC\fR. In doubly-quoted strings, two backslash sequences are recognized: \fB\\\\\fR translates to a single backslash, and \fB\\\(dq\fR translates to a double-quote. .PP Two flags are provided to modify this behavior. If .I WRDSF_CESCAPES flag is set, the following escape sequences are recognized: .sp .nf .ta 8n 18n 42n .ul Sequence Expansion ASCII \fB\\\\\fR \fB\\\fR 134 \fB\\\(dq\fR \fB\(dq\fR 042 \fB\\a\fR audible bell 007 \fB\\b\fR backspace 010 \fB\\f\fR form-feed 014 \fB\\n\fR new line 012 \fB\\r\fR charriage return 015 \fB\\t\fR horizontal tabulation 011 \fB\\v\fR vertical tabulation 013 .fi .sp The sequence \fB\\x\fINN\fR or \fB\\X\fINN\fR, where \fINN\fR stands for a two-digit hex number is replaced with ASCII character \fINN\fR. The sequence \fB\\0\fINNN\fR, where \fINNN\fR stands for a three-digit octal number is replaced with ASCII character whose code is \fINNN\fR. .PP The \fBWRDSF_ESCAPE\fR flag allows the caller to customize escape sequences. If it is set, the \fBws_escape\fR member must be initialized. This member provides escape tables for unquoted words (\fBws_escape[0]\fR) and quoted strings (\fBws_escape[1]\fR). Each table is a string consisting of an even number of charactes. In each pair of characters, the first one is a character that can appear after backslash, and the following one is its translation. For example, the above table of C escapes is represented as \fB\(dq\\\\\\\\"\\"a\\ab\\bf\\fn\\nr\\rt\\tv\\v\(dq\fR. .PP It is valid to initialize \fBws_escape\fR elements to zero. In this case, no backslash translation occurs. .PP Interpretation of octal and hex escapes is controlled by the following bits in \fBws_options\fR: .TP .B WRDSO_BSKEEP_WORD When an unrecognized escape sequence is encountered in a word, preserve it on output. If that bit is not set, the backslash is removed from such sequences. .TP .B WRDSO_OESC_WORD Handle octal escapes in words. .TP .B WRDSO_XESC_WORD Handle hex escapes in words. .TP .B WRDSO_BSKEEP_QUOTE When an unrecognized escape sequence is encountered in a doubly-quoted string, preserve it on output. If that bit is not set, the backslash is removed from such sequences. .TP .B WRDSO_OESC_QUOTE Handle octal escapes in doubly-quoted strings. .TP .B WRDSO_XESC_QUOTE Handle hex escapes in doubly-quoted strings. .SS Command substitution During \fIcommand substitution\fR, each word is scanned for commands. Each command found is executed and replaced by the output it creates. .PP The syntax is: .PP .RS +4 .BI $( command ) .RE .PP Command substitutions may be nested. .PP Unless the substitution appears within double quotes, word splitting and pathname expansion are performed on its result. .PP To enable command substitution, the caller must initialize the .I ws_command member with the address of the substitution function and make sure the .B WRDSF_NOCMD flag is not set. .PP The substitution function should be defined as follows: .PP .RS +4 \fBint \fIcommand\fB\ (char **\fIret\fB,\ const char *\fIcmd\fB,\ size_t \fIlen,\fB\ char **\fIargv\fB,\ void *\fIclos\fB);\fR .RE .PP On input, the first \fIlen\fR bytes of \fIcmd\fR contain the command invocation as it appeared between .BR $( " and " ), with all expansions performed. .PP The \fIargv\fR parameter contains the command line split into words using the same settings as the input \fIws\fR structure. .PP The \fIclos\fR parameter supplies user-specific data, passed in the \fIws_closure\fR member). .PP On success, the function stores a pointer to the output string in the memory location pointed to by \fIret\fR and returns \fBWRDSE_OK\fR (\fB0\fR). On error, it must return one of the error codes described in the section .BR "ERROR CODES" . If .BR WRDSE_USERERR , is returned, a pointer to the error description string must be stored in .BR *ret . .PP When \fBWRDSE_OK\fR or \fBWRDSE_USERERR\fR is returned, the data stored in \fB*ret\fR must be allocated using .BR malloc (3). .SS Tilde and pathname expansion Both expansions are performed if the .B WRDSF_PATHEXPAND flag is set. .PP .I Tilde expansion affects any word that begins with an unquoted tilde character (\fB~\fR). If the tilde is followed immediately by a slash, it is replaced with the home directory of the current user (as determined by his \fBpasswd\fR entry). A tilde alone is handled the same way. Otherwise, the characters between the tilde and first slash character (or end of string, if it doesn't contain any) are treated as a login name. and are replaced (along with the tilde itself) with the home directory of that user. If there is no user with such login name, the word is left unchanged. .PP During .I pathname expansion each unquoted word is scanned for characters .BR * ", " ? ", and " [ . If any of these appears, the word is considered a \fIpattern\fR (in the sense of .BR glob (3)) and is replaced with an alphabetically sorted list of file names matching the pattern. .PP If no matches are found for a word and the \fIws_options\fR member has the .B WRDSO_NULLGLOB bit set, the word is removed. .PP If the \fBWRDSO_FAILGLOB\fR option is set, an error message is output for each such word using .IR ws_error . .PP When matching a pattern, the dot at the start of a name or immediately following a slash must be matched explicitly, unless the \fBWRDSO_DOTGLOB\fR option is set. .SH LIMITING THE NUMBER OF WORDS The maximum number of words to be returned can be limited by setting the \fBws_maxwords\fR member to the desired count, and setting the \fBWRDSO_MAXWORDS\fR option, e.g.: .sp .EX struct wordsplit ws; ws.ws_maxwords = 3; ws.ws_options = WRDSO_MAXWORDS; wordsplit(str, &ws, WRDSF_DEFFLAGS|WRDSF_OPTIONS); .EE .PP If the actual number of words in the expanded input is greater than the supplied limit, the trailing part of the input will be returned in the last word. For example, if the input to the above fragment were \fBNow is the time for all good men\fR, then the returned words would be: .sp .EX "Now" "is" "the time for all good men" .EE .SH WORDSPLIT_T STRUCTURE The data type \fBwordsplit_t\fR has three members that contain output data upon return from \fBwordsplit\fR or \fBwordsplit_len\fR, and a number of members that the caller can initialize on input in order to customize the function behavior. For each input member there is a corresponding flag bit, which must be set in the \fIflags\fR argument in order to instruct the \fBwordsplit\fR function to use the member. .SS OUTPUT .TP .BI size_t " ws_wordc" Number of words in \fIws_wordv\fR. Accessible upon successful return from \fBwordsplit\fR. .TP .BI "char ** " ws_wordv Array of resulting words. Accessible upon successful return from \fBwordsplit\fR. .PP The caller should not attempt to free or reallocate \fIws_wordv\fR or any elements thereof, nor to modify \fIws_wordc\fR. .PP To store away the words for use after freeing \fIws\fR with .BR wordsplit_free , the caller should use .BR wordsplit_getwords . It is more effective than copying the contents of .I ws_wordv manually. .TP .BI "size_t " ws_wordi Total number of words processed. This field is intended for use with .B WRDSF_INCREMENTAL flag. If that flag is not set, the following relation holds: .BR "ws_wordi == ws_wordc - ws_offs" . .TP .BI "int " ws_errno Error code, if the invocation of \fBwordsplit\fR or \fBwordsplit_len\fR failed. This is the same value as returned from the function in that case. .TP .BI "char *" ws_errctx On error, context in which the error occurred. For .BR WRDSE_UNDEF , it is the name of the undefined variable. For .B WRDSE_GLOBERR - the pattern that caused error. .sp The caller should treat this member as .BR "const char *" . .PP The following members are used if the variable expansion was requested and the input string contained an .B Assign Default Values form (\fB${\fIvariable\fB:=\fIword\fB}\fR). .TP .BI "char **" ws_envbuf Modified environment. It follows the same arrangement as \fIws_env\fR on input (see the \fBWRDSF_ENV_KV\fR flag). If \fIws_env\fR was NULL (or \fBWRDSF_ENV\fR was not set), but the \fIws_getvar\fR callback was used, the \fIws_envbuf\fR array will contain only the modified variables. .TP .BI "size_t " ws_envidx Number of entries in .IR ws_envbuf . .PP If positional parameters were used (see the \fBWRDSO_PARAMV\fR option) and any of them were modified during processing, the following two members supply the modified parameter array. .TP .BI "char ** " ws_parambuf Array of positional parameters. .TP .BI "size_t " ws_paramidx Number of positional parameters. .SS INPUT .TP .BI "size_t " ws_offs If the .B WRDSF_DOOFFS flag is set, this member specifies the number of initial elements in .I ws_wordv to fill with NULLs. These elements are not counted in the returned .IR ws_wordc . .TP .BI "size_t " ws_maxwords Maximum number of words to return. For this field to take effect, the \fBWRDSO_MAXWORDS\fR option and \fBWRDSF_OPTIONS\fR flag must be set. For a detailed discussion, see the chapter .BR "LIMITING THE NUMBER OF WORDS" . .TP .BI "int " ws_flags Contains flags passed to wordsplit on entry. Can be used as a read-only member when using \fBwordsplit\fR in incremental mode or in a loop with .B WRDSF_REUSE flag set. .TP .BI "int " ws_options Additional options used when .B WRDSF_OPTIONS is set. .TP .BI "const char *" ws_delim Word delimiters. If initialized on input, the .B WRDSF_DELIM flag must be set. Otherwise, it is initialized on entry to .B wordsplit with the string \fB\(dq \\t\\n\(dq\fR. .TP .BI "const char *" ws_comment A zero-terminated string of characters that begin an inline comment. If initialized on input, the .B WRDSF_COMMENT flag must be set. By default, it's value is \fB\(dq#\(dq\fR. .TP .BI "const char *" ws_escape [2] Escape tables for unquoted words (\fBws_escape[0]\fR) and quoted strings (\fBws_escape[1]\fR). These are used to translate escape sequences (\fB\\\fIC\fR) into characters. Each table is a string consisting of even number of charactes. In each pair of characters, the first one is a character that can appear after backslash, and the following one is its representation. For example, the string \fB\(dqt\\tn\\n\(dq\fR translates \fB\\t\fR into horisontal tabulation character and \fB\\n\fR into newline. .B WRDSF_ESCAPE flag must be set if this member is initialized. .TP .BI "void (*" ws_alloc_die ") (wordsplit_t *)" This function is called when .B wordsplit is unable to allocate memory and the .B WRDSF_ENOMEMABRT flag was set. The default function prints a message on standard error and aborts. This member can be used to customize error handling. If initialized, the .B WRDSF_ALLOC_DIE flag must be set. .TP .BI "void (*" ws_error ") (const char *, ...)" Pointer to function used for error reporting. The invocation convention is the same as for .BR printf (3). The default function formats and prints the message on the standard error. If this member is initialized, the .B WRDSF_ERROR flag must be set. .TP .BI "void (*" ws_debug ") (const char *, ...)" Pointer to function used for debugging output. By default it points to the same function as .BR ws_error . If initialized, the .B WRDSF_DEBUG flag must be set. .TP .BR "const char **" ws_env A \fBNULL\fR-terminated array of environment variables. It is used during variable expansion. If set, the .B WRDSF_ENV flag must be set. Variable expansion is enabled only if either .B WRDSF_ENV or .B WRDSF_GETVAR (see below) is set, and .B WRDSF_NOVAR flag is not set. Each element of .I ws_env must have the form \fB\(dq\fINAME\fB=\fIVALUE\fR, where \fINAME\fR is the name of the variable, and \fIVALUE\fR is its value. Alternatively, if the \fBWRDSF_ENV_KV\fR flag is set, each variable is described by two elements of .IR ws_env : one containing variable name, and the next one with its value. .TP .BI "int (*" ws_getvar ") (char **ret, const char *var, size_t len, void *clos)" Points to the function that will be used during variable expansion for environment variable lookups. This function is used if the variable expansion is enabled (i.e. the .B WRDSF_NOVAR flag is not set), and the \fBWRDSF_GETVAR\fR flag is set. .sp If both .B WRDSF_ENV and .B WRDSF_GETVAR are set, the variable is first looked up in the .I ws_env array and, if not found there, .I ws_getvar is called. If the \fBWRDSO_GETVARPREF\fR option is set, this order is reverted. .sp The name of the variable is specified by the first \fIlen\fR bytes of the string \fIvar\fR. The \fIclos\fR parameter supplies the user-specific data (see below the description of \fIws_closure\fR member) and the \fBret\fR parameter points to the memory location where output data is to be stored. On success, the function must store there a pointer to the string with the value of the variable and return 0. On error, it must return one of the error codes described in the section .BR "ERROR CODES" . If \fIws_getvar\fR returns .BR WRDSE_USERERR , it must store the pointer to the error description string in .BR *ret . In any case (whether returning \fB0\fR or \fBWRDSE_USERERR\fR), the data returned in \fBret\fR must be allocated using .BR malloc (3). .TP .BI "void *" ws_closure Additional user-specific data passed as the last argument to .I ws_getvar or .I ws_command (see below). If defined, the .B WRDSF_CLOSURE flag must be set. .TP \fBint (*\fIws_command\fB)\ (char **ret,\ const char *cmd,\ size_t len,\ char **argv,\ void *clos)\fR Pointer to the function that performs command substitution. It treats the first \fIlen\fR bytes of the string \fIcmd\fR as a command (whatever it means for the caller) and attempts to execute it. On success, a pointer to the string with the command output is stored in the memory location pointed to by \fBret\fR and \fB0\fR is returned. On error, the function must return one of the error codes described in the section .BR "ERROR CODES" . If \fIws_command\fR returns .BR WRDSE_USERERR , it must store the pointer to the error description string in .BR *ret . In any case (whether returning \fB0\fR or \fBWRDSE_USERERR\fR), the data returned in \fBret\fR must be allocated using .BR malloc (3). The parameter \fBargv\fR contains the command split into words using the same settings as the input \fIws\fR structure, with command substitution disabled. The \fIclos\fR parameter supplies user-specific data (see the description of \fIws_closure\fR member). .PP The following two members are consulted if the \fBWRDSO_PARAMV\fR option is set. They provide an array of positional parameters. .TP .BI "char const **" ws_paramv Positional parameters. These are accessible in the input string using the notation \fB$\fIN\fR or \fB${\fIN\fB}\fR, where \fIN\fR is the 0-based parameter number. .TP .BI "size_t " ws_paramc Number of positional parameters. .SH FLAGS The following macros are defined for use in the \fBflags\fR argument. .TP .B WRDSF_DEFFLAGS Default flags. This is a shortcut for: \fB(WRDSF_NOVAR |\ WRDSF_NOCMD |\ WRDSF_QUOTE |\ WRDSF_SQUEEZE_DELIMS |\ WRDSF_CESCAPES)\fR, i.e.: disable variable expansion and quote substituton, perform quote removal, treat any number of consequtive delimiters as a single delimiter, replace \fBC\fR escapes appearing in the input string with the corresponding characters. .TP .B WRDSF_APPEND Append the resulting words to the array left from a previous call to \fBwordsplit\fR. .TP .B WRDSF_DOOFFS Insert .I ws_offs initial .BR NULL s in the array .IR ws_wordv . These are not counted in the returned .IR ws_wordc . .TP .B WRDSF_NOCMD Don't do command substitution. The \fBWRDSO_NOCMDSPLIT\fR option set together with this flag prevents splitting command invocations into separate words (see the \fBOPTIONS\fR section). .TP .B WRDSF_REUSE The parameter \fIws\fR resulted from a previous call to \fBwordsplit\fR, and \fBwordsplit_free\fR was not called. Reuse the allocated storage. .TP .B WRDSF_SHOWERR Print errors using .BR ws_error . .TP .B WRDSF_UNDEF Consider it an error if an undefined variable is expanded. .TP .B WRDSF_NOVAR Don't do variable expansion. The \fBWRDSO_NOVARSPLIT\fR option set together with this flag prevents variable references from being split into separate words (see the \fBOPTIONS\fR section). .TP .B WRDSF_ENOMEMABRT Abort on .B ENOMEM error. By default, out of memory errors are treated as any other errors: the error is reported using \fIws_error\fR if the .B WRDSF_SHOWERR flag is set, and error code is returned. If this flag is set, the .B ws_alloc_die function is called instead. This function is not supposed to return. .TP .B WRDSF_WS Trim off any leading and trailind whitespace from the returned words. This flag is useful if the \fIws_delim\fR member does not contain whitespace characters. .TP .B WRDSF_SQUOTE Handle single quotes. .TP .B WRDSF_DQUOTE Handle double quotes. .TP .B WRDSF_QUOTE A shortcut for \fB(WRDSF_SQUOTE|WRDSF_DQUOTE)\fR. .TP .B WRDSF_SQUEEZE_DELIMS Replace each input sequence of repeated delimiters with a single delimiter. .TP .B WRDSF_RETURN_DELIMS Return delimiters. .TP .B WRDSF_SED_EXPR Treat .BR sed (1) expressions as words. .TP .B WRDSF_DELIM .I ws_delim member is initialized. .TP .B WRDSF_COMMENT .I ws_comment member is initialized. .TP .B WRDSF_ALLOC_DIE .I ws_alloc_die member is initialized. .TP .B WRDSF_ERROR .I ws_error member is initialized. .TP .B WRDSF_DEBUG .I ws_debug member is initialized. .TP .B WRDSF_ENV .I ws_env member is initialized. .TP .B WRDSF_GETVAR .I ws_getvar member is initialized. .TP .B WRDSF_SHOWDBG Enable debugging. .TP .B WRDSF_NOSPLIT Don't split input into words. This flag is is useful for side effects, e.g. to perform variable expansion within a string. .TP .B WRDSF_KEEPUNDEF Keep undefined variables in place, instead of expanding them to empty strings. .TP .B WRDSF_WARNUNDEF Warn about undefined variables. .TP .B WRDSF_CESCAPES Handle \fBC\fR-style escapes in the input string. .TP .B WRDSF_CLOSURE .I ws_closure is set. .TP .B WRDSF_ENV_KV Each two consecutive elements in the .I ws_env array describe a single variable: .IR ws_env [ n ] contains variable name, and .IR ws_env [ "n+1" ] contains its value. .TP .B WRDSF_ESCAPE .I ws_escape is set. .TP .B WRDSF_INCREMENTAL Incremental mode. Each subsequent call to \fBwordsplit\fR with \fBNULL\fR as its first argument parses the next word from the input. See the section .B INCREMENTAL MODE for a detailed discussion. .TP .B WRDSF_PATHEXPAND Perform pathname and tilde expansion. See the subsection .B "Pathname expansion" for details. .TP .B WRDSF_OPTIONS The .I ws_options member is initialized. .SH OPTIONS The .I ws_options member is consulted if the .B WRDSF_OPTIONS flag is set. It contains a bitwise \fBOR\fR of one or more of the following options: .TP .B WRDSO_NULLGLOB Remove the words that produce empty string after pathname expansion. .TP .B WRDSO_FAILGLOB Output error message if pathname expansion produces empty string. .TP .B WRDSO_DOTGLOB During pathname expansion allow a leading period to be matched by metacharacters. .PP .TP .B WRDSO_BSKEEP_WORD Backslash interpretation: when an unrecognized escape sequence is encountered in a word, preserve it on output. If that bit is not set, the backslash is removed from such sequences. .TP .B WRDSO_OESC_WORD Backslash interpretation: handle octal escapes in words. .TP .B WRDSO_XESC_WORD Backslash interpretation: handle hex escapes in words. .TP .B WRDSO_BSKEEP_QUOTE Backslash interpretation: when an unrecognized escape sequence is encountered in a doubly-quoted string, preserve it on output. If that bit is not set, the backslash is removed from such sequences. .TP .B WRDSO_OESC_QUOTE Backslash interpretation: handle octal escapes in doubly-quoted strings. .TP .B WRDSO_XESC_QUOTE Backslash interpretation: handle hex escapes in doubly-quoted strings. .TP .B WRDSO_MAXWORDS The \fBws_maxwords\fR member is initialized. This is used to control the number of words returned by a call to \fBwordsplit\fR. For a detailed discussion, refer to the chapter .BR "LIMITING THE NUMBER OF WORDS" . .TP .B WRDSO_NOVARSPLIT When \fBWRDSF_NOVAR\fR is set, don't split variable references, even if they contain whitespace. E.g. .B ${VAR:-foo bar} will be treated as a single word. .TP .B WRDSO_NOCMDSPLIT When \fBWRDSF_NOCMD\fR is set, don't split whatever looks like command invocation, even if it contains whitespace. E.g. .B $(command arg) will be treated as a single word. .TP .B WRDSO_PARAMV Positional arguments are supplied in .I ws_paramv and .IR ws_paramc . See the subsection .B Positional argument expansion for a discussion. .TP .B WRDSO_PARAM_NEGIDX Used together with \fBWRDSO_PARAMV\fR, this allows for negative positional argument references. A negative argument reference has the form \fB${-\fIN\fB}\fR. It is expanded to the value of the argument with index \fB\fIws_paramc\fR \- \fIN\fR, i.e. \fIN\fRth if counting from the end. .SH "ERROR CODES" .TP .BR WRDSE_OK ", " WRDSE_EOF Successful return. .TP .B WRDSE_QUOTE Missing closing quote. The \fIws_endp\fR points to the position in the input string where the error occurred. .TP .B WRDSE_NOSPACE Memory exhausted. .TP .B WRDSE_USAGE Invalid wordsplit usage. .TP .B WRDSE_CBRACE Unbalanced curly brace. .TP .B WRDSE_UNDEF Undefined variable. This error is returned only if the \fBWRDSF_UNDEF\fR flag is set. .TP .B WRDSE_NOINPUT Input exhausted. This is not acually an error. This code is returned if \fBwordsplit\fR (or \fBwordsplit_len\fR) is invoked in incremental mode and encounters end of input string. See the section .BR "INCREMENTAL MODE" . .TP .B WRDSE_PAREN Unbalanced parenthesis. .TP .B WRDSE_GLOBERR An error occurred during pattern matching. .TP .B WRDSE_USERERR User-defined error. Normally this error is returned by \fBws_getvar\fR or \fBws_command\fR. Use the function .B wordsplit_strerror to get textual description of the error. .SH "RETURN VALUE" Both .B wordsplit and .B wordsplit_len return \fB0\fR on success, and a non-zero error code on error (see the section .BR "ERROR CODES" ). .PP .B wordsplit_strerror returns a pointer to the constant string describing the last error condition that occurred in .IR ws . .SH EXAMPLE The short program below implements a function that parses the input string similarly to the shell. All expansions are performed. Default error reporting is used. .PP .EX #include #include #include #include #include /* Run command from \fIstr\fR (\fIlen\fR bytes long) and store its output in \fIret\fR. \fIargv\fR and \fIclosure\fR are not used. Return wordsplit error code. */ static int runcmd(char **ret, const char *str, size_t len, char **argv, void *closure) { FILE *fp; char *cmd; int c, lastc; char *buffer = NULL; size_t bufsize = 0; size_t buflen = 0; /* Convert to a null-terminated string for \fBpopen\fR(3) */ cmd = malloc(len + 1); if (!cmd) return WRDSE_NOSPACE; memcpy(cmd, str, len); cmd[len] = 0; fp = popen(cmd, "r"); if (!fp) { char buf[128]; snprintf(buf, sizeof buf, "can't run %s: %s", cmd, strerror(errno)); *ret = strdup(buf); if (!*ret) return WRDSE_NOSPACE; else return WRDSE_USERERR; } /* Collect the output, reallocating \fIbuffer\fR as needed. */ while ((c = fgetc(fp)) != EOF) { lastc = c; if (c == '\n') c = ' '; if (buflen == bufsize) { char *p; if (bufsize == 0) bufsize = 80; else bufsize *= 2; p = realloc(buffer, bufsize); if (!p) { free(buffer); free(cmd); return WRDSE_NOSPACE; } buffer = p; } buffer[buflen++] = c; } /* Tream off the trailing newline */ if (buffer) { if (lastc == '\n') --buflen; buffer[buflen] = 0; } pclose(fp); free(cmd); /* Return the composed string. */ *ret = buffer; return WRDSE_OK; } extern char **environ; /* Parse \fIs\fR much as shell does. Return array of words on succes, and NULL on error. */ char **shell_parse(char *s) { wordsplit_t ws; size_t wc; char **wv; int rc; /* Initialize \fIws\fR */ ws.ws_env = (const char **) environ; ws.ws_command = runcmd; /* Call \fBwordsplit\fR. Let it report errors, if any. */ rc = wordsplit(s, &ws, WRDSF_QUOTE | WRDSF_SQUEEZE_DELIMS | WRDSF_PATHEXPAND | WRDSF_SHOWERR); if (rc == WRDSE_OK) /* Store away the resulting words on success. */ wordsplit_getwords(&ws, &wc, &wv); else wv = NULL; wordsplit_free(&ws); return wv; } .EE .SH AUTHORS Sergey Poznyakoff .SH BUGS Backtick command expansion is not supported. .SH "BUG REPORTS" Report bugs to . .SH COPYRIGHT Copyright \(co 2009-2019 Sergey Poznyakoff .br .na License GPLv3+: GNU GPL version 3 or later .br .ad This is free software: you are free to change and redistribute it. There is NO WARRANTY, to the extent permitted by law. .\" Local variables: .\" eval: (add-hook 'write-file-hooks 'time-stamp) .\" time-stamp-start: ".TH [A-Z_][A-Z0-9_]* [0-9] \"" .\" time-stamp-format: "%:B %:d, %:y" .\" time-stamp-end: "\"" .\" time-stamp-line-limit: 20 .\" end: