Brian Silverman | 70325d6 | 2015-09-20 17:00:43 -0400 | [diff] [blame] | 1 | # Copyright (c) 2008, Google Inc. |
| 2 | # All rights reserved. |
| 3 | # |
| 4 | # Redistribution and use in source and binary forms, with or without |
| 5 | # modification, are permitted provided that the following conditions are |
| 6 | # met: |
| 7 | # |
| 8 | # * Redistributions of source code must retain the above copyright |
| 9 | # notice, this list of conditions and the following disclaimer. |
| 10 | # * Redistributions in binary form must reproduce the above |
| 11 | # copyright notice, this list of conditions and the following disclaimer |
| 12 | # in the documentation and/or other materials provided with the |
| 13 | # distribution. |
| 14 | # * Neither the name of Google Inc. nor the names of its |
| 15 | # contributors may be used to endorse or promote products derived from |
| 16 | # this software without specific prior written permission. |
| 17 | # |
| 18 | # THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS |
| 19 | # "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT |
| 20 | # LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR |
| 21 | # A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT |
| 22 | # OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, |
| 23 | # SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT |
| 24 | # LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, |
| 25 | # DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY |
| 26 | # THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT |
| 27 | # (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE |
| 28 | # OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. |
| 29 | # --- |
| 30 | # |
| 31 | # Author: falmeida@google.com (Filipe Almeida) |
| 32 | |
| 33 | name = 'jsparser' |
| 34 | |
| 35 | comment = 'Simplified finite state machine for tracking of javascript states' |
| 36 | |
| 37 | condition('q', '\''), |
| 38 | condition('dq', '\"'), |
| 39 | condition('/', '/'), |
| 40 | condition('*', '*'), |
| 41 | condition('[', '['), |
| 42 | condition(']', ']'), |
| 43 | condition('lf', '\n'), |
| 44 | condition('backslash', '\\'), |
| 45 | condition('default', '[:default:]') |
| 46 | |
| 47 | # Main javascript body. |
| 48 | state(name = 'js_text', |
| 49 | external = 'text', |
| 50 | transitions = [ |
| 51 | ['q', 'js_q'], |
| 52 | ['dq', 'js_dq'], |
| 53 | ['/', 'js_slash'], |
| 54 | ['default', 'js_text'] |
| 55 | ]) |
| 56 | |
| 57 | # Single quoted string literal. |
| 58 | state(name = 'js_q', |
| 59 | external = 'q', |
| 60 | transitions = [ |
| 61 | ['backslash', 'js_q_e'], |
| 62 | ['q', 'js_text'], |
| 63 | ['default', 'js_q'] |
| 64 | ]) |
| 65 | |
| 66 | # Javascript escaped character in a single quoted string literal. |
| 67 | state(name = 'js_q_e', |
| 68 | external = 'q', |
| 69 | transitions = [ |
| 70 | ['default', 'js_q'] |
| 71 | ]) |
| 72 | |
| 73 | # Double quoted string literal |
| 74 | state(name = 'js_dq', |
| 75 | external = 'dq', |
| 76 | transitions = [ |
| 77 | ['backslash', 'js_dq_e'], |
| 78 | ['dq', 'js_text'], |
| 79 | ['default', 'js_dq'] |
| 80 | ]) |
| 81 | |
| 82 | # Javascript escaped character in a double quoted string literal. |
| 83 | state(name = 'js_dq_e', |
| 84 | external = 'dq', |
| 85 | transitions = [ |
| 86 | ['default', 'js_dq'] |
| 87 | ]) |
| 88 | |
| 89 | # Possible start of a javascript comment. |
| 90 | state(name = 'js_slash', |
| 91 | external = 'text', |
| 92 | transitions = [ |
| 93 | ['/', 'js_comment_ln'], |
| 94 | ['*', 'js_comment_ml'], |
| 95 | ['default', 'js_text'] |
| 96 | ]) |
| 97 | |
| 98 | # Possible start of a regular expression literal. |
| 99 | # |
| 100 | # The state diagram does not reach this state directly. When js_slash is |
| 101 | # reached, the function enter_state_js_slash() is called, which checks if the |
| 102 | # last token belongs to the set of tokens that can precede a regular |
| 103 | # expression, in which case it changes the state to js_regexp_slash. |
| 104 | # |
| 105 | # For more information please read the comments in |
| 106 | # jsparser.c:enter_state_js_slash(). |
| 107 | state(name = 'js_regexp_slash', |
| 108 | external = 'text', |
| 109 | transitions = [ |
| 110 | ['/', 'js_comment_ln'], |
| 111 | ['*', 'js_comment_ml'], |
| 112 | ['backslash', 'js_regexp_e'], |
| 113 | ['[', 'js_regexp_bracket'], |
| 114 | ['default', 'js_regexp'] |
| 115 | ]) |
| 116 | |
| 117 | # Regular expression literal. |
| 118 | state(name = 'js_regexp', |
| 119 | external = 'regexp', |
| 120 | transitions = [ |
| 121 | ['backslash', 'js_regexp_e'], |
| 122 | ['[', 'js_regexp_bracket'], |
| 123 | ['/', 'js_text'], |
| 124 | ['default', 'js_regexp'] |
| 125 | ]) |
| 126 | |
| 127 | # Regexp bracket expression |
| 128 | state(name = 'js_regexp_bracket', |
| 129 | external = 'regexp', |
| 130 | transitions = [ |
| 131 | ['backslash', 'js_regexp_bracket_e'], |
| 132 | [']', 'js_regexp'], |
| 133 | ['default', 'js_regexp_bracket'] |
| 134 | ]) |
| 135 | |
| 136 | # Backslash escaped regexp bracket expression |
| 137 | state(name = 'js_regexp_bracket_e', |
| 138 | external = 'regexp', |
| 139 | transitions = [ |
| 140 | ['default', 'js_regexp_bracket'] |
| 141 | ]) |
| 142 | |
| 143 | # Escaped regular expression char. |
| 144 | state(name = 'js_regexp_e', |
| 145 | external = 'regexp', |
| 146 | transitions = [ |
| 147 | ['default', 'js_regexp'] |
| 148 | ]) |
| 149 | |
| 150 | # Start of a single line javascript comment (//). |
| 151 | state(name = 'js_comment_ln', |
| 152 | external = 'comment', |
| 153 | transitions = [ |
| 154 | ['lf', 'js_comment_after'], |
| 155 | ['default', 'js_comment_ln'] |
| 156 | ]) |
| 157 | |
| 158 | # Start of a multiline javascript comment (/*). |
| 159 | state(name = 'js_comment_ml', |
| 160 | external = 'comment', |
| 161 | transitions = [ |
| 162 | ['*', 'js_comment_ml_close'], |
| 163 | ['default', 'js_comment_ml'] |
| 164 | ]) |
| 165 | |
| 166 | # Close of a multiline javascript comment (*/). |
| 167 | state(name = 'js_comment_ml_close', |
| 168 | external = 'comment', |
| 169 | transitions = [ |
| 170 | ['/', 'js_comment_after'], |
| 171 | ['default', 'js_comment_ml'] |
| 172 | ]) |
| 173 | |
| 174 | # Ending character of a javascript comment. |
| 175 | # In can either be a '/ in the case of a multiline comment, or a line |
| 176 | # terminator in the case of a single line comment. |
| 177 | # This is needed so we don't insert the '/' or the new line character into the |
| 178 | # ring buffer. |
| 179 | state(name = 'js_comment_after', |
| 180 | external = 'text', |
| 181 | transitions = [ |
| 182 | ['q', 'js_q'], |
| 183 | ['dq', 'js_dq'], |
| 184 | ['/', 'js_slash'], |
| 185 | ['default', 'js_text'] |
| 186 | ]) |