xref: /OpenGrok/opengrok-indexer/src/main/jflex/analysis/tcl/Tcl.lexh (revision d219b4cea555a12b602d2d5518daa22134ad4879)

/*
 * CDDL HEADER START
 *
 * The contents of this file are subject to the terms of the
 * Common Development and Distribution License (the "License").
 * You may not use this file except in compliance with the License.
 *
 * See LICENSE.txt included in this distribution for the specific
 * language governing permissions and limitations under the License.
 *
 * When distributing Covered Code, include this CDDL HEADER in each
 * file and include the License file at LICENSE.txt.
 * If applicable, add the following below this CDDL HEADER, with the
 * fields enclosed by brackets "[]" replaced with your own identifying
 * information: Portions Copyright [yyyy] [name of copyright owner]
 *
 * CDDL HEADER END
 */

/*
 * Copyright (c) 2008, 2016, Oracle and/or its affiliates. All rights reserved.
 * Portions Copyright (c) 2017, Chris Fraire <cfraire@me.com>.
 *
 * Copyright © 1993 The Regents of the University of California.
 * Copyright © 1994-1996 Sun Microsystems, Inc.
 * Copyright © 1995-1997 Roger E. Critchlow Jr.
 */

Number = ([0-9]+\.[0-9]+|[0-9][0-9]*|"#" [boxBOX] [0-9a-fA-F]+)

/*
 * [1] Commands. ... Semi-colons and newlines are command separators unless
 * quoted as described below.
 *
 * [3] Words. Words of a command are separated by white space (except for
 * newlines, which are command separators).
 * [4] Double quotes. If the first character of a word is double-quote (``"'')
 * then the word is terminated by the next double-quote character.
 * [5] Braces. If the first character of a word is an open brace (``{'') then
 * the word is terminated by the matching close brace (``}'').
 *  N.b. OpenGrok handles [4] and [5] as special matches distinct from {Word}.
 *
 * [9] Comments. If a hash character (``#'') appears at a point where Tcl is
 * expecting the first character of the first word of a command, then the hash
 * character and the characters that follow it, up through the next newline,
 * are treated as a comment and ignored. The comment character only has
 * significance when it appears at the beginning of a command.
 *
 * N.b. this "OrdinaryWord" is for OpenGrok's purpose of symbol tokenization
 * and deviates from the above definitions by treating backslash escapes as
 * word breaking and precluding some characters from starting words and mostly
 * the same from continuing words. E.g., hyphen is not allowed by OpenGrok to
 * start OrdinaryWord but can be present afterward.
 */
OrdinaryWord = [\S--\-,=#\"\}\{\]\[\)\(\\] [\S--#\"\}\{\]\[\)\(\\]*

/*
 * [7] Variable substitution.
 *
 * $name
 *     Name is the name of a scalar variable; the name is a sequence of one or
 *     more characters that are a letter, digit, underscore, or namespace
 *     separators (two or more colons).
 */
Varsub1 = \$ {name_unit}+
name_unit = ([\p{Letter}\p{Digit}_] | [:][:]+)
/*
 * $name(index)
 *     Name gives the name of an array variable and index gives the name of an
 *     element within that array. Name must contain only letters, digits,
 *     underscores, and namespace separators, and may be an empty string.
 */
Varsub2 = \$ {name_unit}* \( {name_unit}+ \)
/*
 * ${name}
 *     Name is the name of a scalar variable. It may contain any characters
 *     whatsoever except for close braces.
 */
Varsub3 = \$\{ [^\}]+ \}

/*
 * [8] Backslash substitution.
 * Backslash plus a character, where ... in all cases but [for the characters]
 * described below, the backslash is dropped and the following character is
 * treated as an ordinary character and included in the word.
 *
 * Special cases:
 * a,f,b,n,r,t,v,backslash;
 * \<newline>whiteSpace;
 * \ooo The digits ooo (one, two, or three of them);
 * \xhh The hexadecimal digits hh .... Any number of hexadecimal digits may be
 *     present;
 * \uhhhh The hexadecimal digits hhhh (one, two, three, or four of them)
 *
 * "Backslash substitution is not performed on words enclosed in braces, except
 * for backslash-newline as described above."
 */
Backslash_sub = [\\] ([afbnrtv\\] | \p{Number}{1,3} | [x][0-9a-fA-F]+ |
    [u][0-9a-fA-F]{1,4} | [[^]--[afbnrtv\n\p{Number}xu\\]])
Backslash_nl = [\\] \n\s+

WordOperators = ("*" | "&&" | "||")