| 1 |
<?xml version="1.0" encoding="UTF-8"?> |
| 2 |
<!-- [Purpose & Copyright] |
| 3 |
|
| 4 |
Highlight ISO-Prolog texts or template/include for Prolog dialects |
| 5 |
based on the ISO standard. |
| 6 |
|
| 7 |
Includes detection of DCG since it is 'hooked' in the ISO standard. |
| 8 |
Uses text style "Warning/ISO-bogus" where portability is likely to |
| 9 |
fail. |
| 10 |
|
| 11 |
This file is part of KDE's kate project. |
| 12 |
|
| 13 |
copyright : (C) 2012 by Torsten Eichstädt |
| 14 |
|
| 15 |
********************************************************************** |
| 16 |
* This library is free software; you can redistribute it and/or * |
| 17 |
* modify it under the terms of the GNU Library General Public * |
| 18 |
* License as published by the Free Software Foundation; either * |
| 19 |
* version 2 of the License, or (at your option) any later version. * |
| 20 |
* * |
| 21 |
* This library is distributed in the hope that it will be useful, * |
| 22 |
* but WITHOUT ANY WARRANTY; without even the implied warranty of * |
| 23 |
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU * |
| 24 |
* Library General Public License for more details. * |
| 25 |
* * |
| 26 |
* You should have received a copy of the GNU Library General Public * |
| 27 |
* License along with this library; if not, write to the * |
| 28 |
* Free Software Foundation, Inc., 51 Franklin Street, Fifth Floor, * |
| 29 |
* Boston, MA 02110-1301, USA. * |
| 30 |
********************************************************************** |
| 31 |
--> |
| 32 |
<!DOCTYPE language |
| 33 |
[<!-- [Regular Expressions, Character Classes & Important Tokens] |
| 34 |
E.g. the dot "." has so many different meanings (i.e. in an RegExpr 'any char', |
| 35 |
'fullstop' of a clause, etc. pp.) that I decided it's usefull to write these out |
| 36 |
to make the rules more expressive. --> |
| 37 |
|
| 38 |
<!-- RegExpr for graphic tokens. Comment start "/*" is catched earlier. --> |
| 39 |
<!ENTITY gr_char_iso "[#$&*+\-./:<=>?@^~\\]"> |
| 40 |
|
| 41 |
<!-- RegExpr: The highlighting engine always strips newline, so this ok: --> |
| 42 |
<!ENTITY any_nw "[^ \t]"> |
| 43 |
<!ENTITY any "."> |
| 44 |
|
| 45 |
<!-- RegExpr: we want to highlight some graphic tokens: Logic & Control |
| 46 |
fullstop shall not be falsely detected if it is actually a list functor |
| 47 |
comma is catched extra to highlight it as "Normal Text" in an arg_seq |
| 48 |
(and the cut "!" is NOT an op) --> |
| 49 |
<!ENTITY fullstop_iso "\.(?!(\(|&gr_char_iso;))"> |
| 50 |
<!ENTITY logic_control_ops_iso "(;|->|\\\+|:-|=|\\=)(?!&gr_char_iso;)"> |
| 51 |
|
| 52 |
<!-- RegExpr: DCG (not my idea it is not reversed and named 'reduction') --> |
| 53 |
<!ENTITY dcg_production_iso "-->(?!&gr_char_iso;)"> |
| 54 |
|
| 55 |
<!-- RegExpr: partitioning of arithmetic operators: |
| 56 |
- the 1st "arith_compare" always demand arithmetic evaluation |
| 57 |
=> highlight as "Arithmetics". |
| 58 |
- the 2nd only at the right side of "is" or when an arith_compare applies. |
| 59 |
They are used in other contexts as well, e.g. traditionally A-B is used |
| 60 |
for 'a pair of something', the "^" in bagof/3 and setof/3. |
| 61 |
=> highlight as "Arithmetics" only in an arith_expr. |
| 62 |
- the 3rd are true ISO Bogus: it is not specified whether it is arithmetic |
| 63 |
or logical shift, and for bitwise AND, OR and NEG the integer format is |
| 64 |
unspecified => not portable, depend on Prolog implementation. --> |
| 65 |
<!ENTITY arith_compare_iso "(=:=|=\\=|=<|<|>=|>)(?!&gr_char_iso;)"> |
| 66 |
<!ENTITY arith_ops_mixed_iso "(\+|-|\*|\^)(?!&gr_char_iso;)"> |
| 67 |
<!ENTITY arith_ops_int_iso "//(?!&gr_char_iso;)"> |
| 68 |
<!ENTITY arith_ops_float_iso "(/|\*\*)(?!&gr_char_iso;)"> |
| 69 |
<!ENTITY arith_bogus_iso "(/\\|\\/|\\|<<|>>)(?!&gr_char_iso;)"> |
| 70 |
|
| 71 |
<!-- RegExpr: other predefined operators --> |
| 72 |
<!ENTITY predefined_ops_iso "(\?-|==|\\==|@=<|@<|@>=|@>|=\.\.|@|:)(?!&gr_char_iso;)"> |
| 73 |
|
| 74 |
<!-- We treat a number as float if it includes a decimal dot or exponent --> |
| 75 |
<!ENTITY float3_iso "[0-9]+E[+\-]?[0-9]+"> |
| 76 |
<!ENTITY float2_iso "[0-9]+\.[0-9]+"> |
| 77 |
<!ENTITY float1_iso "[0-9]+\.[0-9]+E[+\-]?[0-9]+"> |
| 78 |
|
| 79 |
<!-- RegExpr for esc'd char code in quoted 'strings' e.g. "\007\" --> |
| 80 |
<!ENTITY esc_oct_iso "\\[0-7]+\\"> |
| 81 |
<!ENTITY esc_hex_iso "\\x[a-fA-F0-9]+\\"> |
| 82 |
|
| 83 |
<!-- Char classes for AnyChar, NOT RegExpr: no esc seqs, ranges, etc. pp. here! |
| 84 |
Used to avoid expensive RegExpr whenever possible. --> |
| 85 |
<!-- Not needed: any_alnum_under_iso: use "DetectIdentifier" instead --> |
| 86 |
<!ENTITY any_lower_iso "abcdefghijklmnopqrstuvwxyz"> |
| 87 |
<!ENTITY any_upper_under_iso "ABCDEFGHIJKLMNOPQRSTUVWXYZ_"> |
| 88 |
<!ENTITY any_bin_iso "01"> |
| 89 |
<!ENTITY any_oct_iso "01234567"> |
| 90 |
<!ENTITY any_dec_iso "0123456789"> |
| 91 |
<!ENTITY any_hex_iso "0123456789abcdefABCDEF"> |
| 92 |
<!ENTITY any_graphic_iso "#$&*+-./:<=>?@^~\"> |
| 93 |
|
| 94 |
<!-- Common esc seq in quoted & char code (after "0'"). |
| 95 |
Tab is handled extra. Esc'd newline is catched earlier. --> |
| 96 |
<!ENTITY any_esc_iso "abfnrtv\'`"]"> |
| 97 |
|
| 98 |
<!ENTITY dot "."> |
| 99 |
|
| 100 |
<!-- Some solo chars for DetectChar --> |
| 101 |
<!ENTITY comma ","> |
| 102 |
<!ENTITY cut "!"> |
| 103 |
<!ENTITY bar "|"> |
| 104 |
<!ENTITY tab "	"> |
| 105 |
<!ENTITY bs "\"> |
| 106 |
]> |
| 107 |
<language name="Prolog" section="Sources" |
| 108 |
version="17" kateversion="5.62" |
| 109 |
mimetype="text/x-prolog" |
| 110 |
extensions="*.prolog;*.dcg;*.pro" |
| 111 |
author="Torsten Eichstädt ([email protected])" |
| 112 |
license="LGPLv2+"> |
| 113 |
|
| 114 |
<!-- [Terminology & Abbreviations In The Comments] |
| 115 |
- Literal text is in double quotes "like this", single quotes sometimes used |
| 116 |
for a 'terminus technicus'. |
| 117 |
- "w/", "w/o", "s/t" mean 'with', 'without', and "sometimes" resp. |
| 118 |
- Use "brace" instead of 'bracket'/'parenthesis' for any of "()[]{}" |
| 119 |
- Specify "round", "list/squared", "curly", "opening" and "closing" brace. |
| 120 |
- "quote/quoted/string" mean any of single-, double-, or back-quote(d) |
| 121 |
- "seq" sequence, "nl" newline, "bs" backslash, "q" quote(d), "cc" char code |
| 122 |
- "KISS" Keep it simple, stupid! (be pragmatic) |
| 123 |
- "style" = "attribute" (the applied text style) |
| 124 |
- Keep comments as short as possible and as descriptive as neccessary LOL |
| 125 |
--> |
| 126 |
<!-- [Documentation, Bugs, Limitations & Solutions, TODOs] |
| 127 |
################################################################################ |
| 128 |
All bugs except three by the author. !FOLD THIS AWAY if long comments annoy you. |
| 129 |
|
| 130 |
BUG - Nobody's perfect - If I knew about the bug you found, it would have been |
| 131 |
fixed already. |
| 132 |
one- Indentation-based folding is not reliable (Kate; fixed in KDE 4.9?). |
| 133 |
two- Folding is sometimes broken (Kate?). See SOLUTIONS below. |
| 134 |
three- An optional leading sign is not highlighted as part of the number. |
| 135 |
4 - A float w/o fractional part and exponent is highlighted as an integer. |
| 136 |
5 - Detection of whitespace may not be 100% correct, only space/tab/newline. |
| 137 |
6 - Handling inside arithmetic expressions might not be 100%. See "AL GUSTO". |
| 138 |
inf- see TODOs below. |
| 139 |
|
| 140 |
LIMITS of this parser |
| 141 |
- Highlighting of syntax errors is as intuitive as possible, i.e. for an |
| 142 |
invalid newline highlight the last token before and leading white of the |
| 143 |
next line - but that's not always possible. Use your built-in problem |
| 144 |
solver (between your ears) when you do not know what the exact error is. |
| 145 |
- The parser knows nothing about currently defined dynamic ops, but has to |
| 146 |
respect possible definitions of dynamic ops. That's why: |
| 147 |
- Any sequence of 'graphic chars' (_incl. those containing a dot_) is taken |
| 148 |
as _one_ graphic token, and not - as you might expect - your user-defined |
| 149 |
operator followed by fullstop (or sequence of ops). |
| 150 |
- A single dot in the outmost term of a clause is taken as a fullstop, even |
| 151 |
if it is actually a user-defined operator. |
| 152 |
- Else, a single dot is highlighted as "Warning" because it might be a |
| 153 |
user-def'd op (usually an error, but can not decide w/o current_op/3). |
| 154 |
- Detection of the fullstop relies upon the usual semantics of braces. |
| 155 |
- Axioms of folding capabilities are: the literal fullstop as stop symbol |
| 156 |
and the usual semantics of braces w/ pairs of opening and closing brace. |
| 157 |
?- period. |
| 158 |
uncaught exception: error(existence_error(procedure,current_op/3),highlight/2) |
| 159 |
|
| 160 |
SOLUTIONS |
| 161 |
- Help the parser by puting whitespace (space/tab/nl) here and there, espc. |
| 162 |
after the fullstop, or use quotes; e.g. '/*' does not begin a comment, |
| 163 |
neither does '%', and ***'.' can be two operators. |
| 164 |
Functored syntax should always do, e.g. */*(X,Y) is valid (and does not |
| 165 |
begin a comment). |
| 166 |
- Folding: s/t moving the mouse slightly below the marker shows what you |
| 167 |
want, s/t an empty line helps (or removing an empty line), when it's |
| 168 |
removed regions stay ok, or break auto-folding w/ non-white @begin of |
| 169 |
line. Try a newer kate version. |
| 170 |
|
| 171 |
AL GUSTO (simple changes): |
| 172 |
- Change classification of built-in predicates: adjust the <list> below. |
| 173 |
- Reminder for other changes: solo chars - DetectChar, graphic - RegExpr. |
| 174 |
- bar "|" (solo) is highlighted as "other built-in operator" in lists, else |
| 175 |
"Normal Text". You may safely remove/comment out the rules in contexts |
| 176 |
"term/list/curly" below if you add in in context "operator" or "atomic". |
| 177 |
If it shall be part of user-defined ops, it has to be added to "gr_char", |
| 178 |
and a few rules need adjustment. Search for "&bar;". You may then safely |
| 179 |
add it to "predefined_ops" above (don't forget to escape it). |
| 180 |
- cut "!" (solo) can be adjusted like the bar. |
| 181 |
- comma "," (solo) is "Normal Text" in lists, else "Logic & Control". You |
| 182 |
may safely remove/comment out the rules in "term/nested/list/curly" below |
| 183 |
and handle it in the context "operator". |
| 184 |
- Disable arith_expr: replace "context="arith_expr"" w/ "context="#stay"" |
| 185 |
in the rules in contexts "atomic" and "operator" (two or three occurrences). |
| 186 |
- Disable indentation-based folding: in the section "general"@EOF:"folding". |
| 187 |
- General guidelines: Be nice to slow/old hardware: avoid RegExpr (start w/ |
| 188 |
a RegExpr, test, then find a replacement), else match a RegExpr as late as |
| 189 |
possible - it's expensive, a context switch is relatively cheap. |
| 190 |
Eat as much text as possible in one run, e.g. in comments and quoted we |
| 191 |
use "DetectIdentifier", else the engine would try all rules of the context |
| 192 |
(w/ failure) and eat only one char on each run. |
| 193 |
If your modification is kind of general, upload it and drop me a note. |
| 194 |
|
| 195 |
The simplified syntax below should highlight 99.999% of ISO-Prolog texts |
| 196 |
correctly, as well as many non-ISO Prolog texts. |
| 197 |
Else modify this file. Save with new name in your HOME directory to |
| 198 |
.kde/share/apps/katepart/syntax/prolog-xy.xml You may read the NOTE at the end |
| 199 |
of this file. WARNING: Be careful, though: the highlighting works according to |
| 200 |
it's program code, not neccessarily it's documentation... |
| 201 |
|
| 202 |
DONE- Parse (m)any (!) conforming Prolog texts w/ correct highlighting (LIMITS) |
| 203 |
- Parse any erratic text w/o crash or endless loops and highlight errors |
| 204 |
- Folding for multiline comments, clauses, nested terms, and quoted (LIMITS) |
| 205 |
- Folding inside comments and of 1-line comments and clauses: indentation- |
| 206 |
based like in Python, e.g. |
| 207 |
my_pred(a). % w/ marker@left (western style; depends on your settings) |
| 208 |
my_pred(b). % you can fold |
| 209 |
my_pred(c). % these lines |
| 210 |
Inside clauses (i.e. context "term" and below) only explicit folding for |
| 211 |
braces and quotes applies, except comments. I did not find a better |
| 212 |
solution, since the engine does not provide lookahead to the next line. |
| 213 |
- Additionally, folding with %BEGIN ... %END (iff 1st nonwhite of the line). |
| 214 |
- Classify built-ins (YMMV) for different highlighting, mainly: |
| 215 |
- w/ side effects from 'outside world' (arithmetics, stream I/O,...) |
| 216 |
- w/o side effects, only depend on user's program ('internal world') |
| 217 |
- program logic & control constructs |
| 218 |
- altering the clause knowledge base or Prolog state |
| 219 |
- integer/float/mixed arithmetics, so one can see the type of the result |
| 220 |
- Iff it's an arithmetic expression; else arith ops and built-ins |
| 221 |
are highlighted normal. |
| 222 |
- Incl. Sep2012 DRAFT Technical Corrigendum 2: Prolog - Part 1: General Core |
| 223 |
- Incl. honourable Richard O'Keefe's remarks as warnings as "ISO Bogus". |
| 224 |
- Detect 'shebang' shell scripts, see BUGs |
| 225 |
- Includes alert.xml to highlight alert keywords in comments. |
| 226 |
- Dot "." may be an _unquoted_ user-defined operator in nested terms (but is |
| 227 |
highlighted as "Warning" 'cause it's more likely a typo than an user-def'd |
| 228 |
op) and is only taken as fullstop and highlighted as "Logic & Control" in |
| 229 |
the outmost term of a clause. |
| 230 |
- Über-correct handling of quoted, escape seqs and "0'" (char code integer): |
| 231 |
- detection of valid/invalid newline in quoted 'strings'. |
| 232 |
- highlight whitespace after esc'd newline in quoted so it differs from |
| 233 |
whitespace contained in the quoted 'string'. |
| 234 |
- Highlight esc'd tab and tab in quoted as "Warning" because some text |
| 235 |
editors may convert them to space and it is easy to use "\t" instead. |
| 236 |
- Preliminary: most names end w/ ISO; prepared to be included in syntax |
| 237 |
files adapted for Prolog dialects. |
| 238 |
- The Shebang is highlighted only in the first line (with lineEmptyContext). |
| 239 |
|
| 240 |
FIXME When katepart can supply line numbers, fix the "shebang" rule. |
| 241 |
|
| 242 |
TODO sorted by priority |
| 243 |
1 - [always] Cruise over all FIXMEs. |
| 244 |
2 - Check if comma, cut & bar are really solo chars (where's the red book?). |
| 245 |
3 - Check final Technical Corrigendum 2: Prolog - Part 1: General Core |
| 246 |
4 - Buy ISO Prolog standard - Part 2: Modules. Likely only keywords. Need it |
| 247 |
anyway. |
| 248 |
5 - Make this strict-ISO and a "Prolog (portable)" that includes this file. |
| 249 |
6 - Likewise, adopt for GNU & SWI Prolog and others. |
| 250 |
8 - keywords 'phrase', streams depricated, etc.pp. ==> Prolog (portable). |
| 251 |
9 - Likewise: shebang ==> Prolog (portable). |
| 252 |
10 - Check if shebang can span multiple (escaped) lines. |
| 253 |
11 - Check: all KB altering preds can have side effects (via resource_error)? |
| 254 |
12 - For next two TODOs: ask katepart dev to provide lookahead to the next line |
| 255 |
13 - Folding for consecutive one-line comments [easy? HARD! Impossible.] |
| 256 |
14 - Likewise, folding for consecutive clauses [HARD! Impossible.] |
| 257 |
I can live w/ indentation-based folding as a workaround. Not 100%, but ok. |
| 258 |
15 - +arg_seq (and list): "," as normal text: Detect name( [no layout; easy] |
| 259 |
16 - +Classify meta predicates. |
| 260 |
18 - The dollar "$" is commonly used as the 1st char of (unquoted?) atoms to |
| 261 |
indicate 'internal mode', e.g. to declare a predicate as compile-in. |
| 262 |
Does this mean the dollar is used as if it were a prefix op or is it part |
| 263 |
of the atom? Would be easy to implement. |
| 264 |
19 - Bug #4: could be partly fixed, some built-ins take only float not integer. |
| 265 |
20 - Bug them to better document weakDeliminators (and rename to delimiter ;) |
| 266 |
21 - Adjust doxygen syntax for Prolog (e.g. adapt doxygen-lua), and include it. |
| 267 |
22 - Check if vertical tab is white/layout; are there more non-printables? |
| 268 |
################################################################################ |
| 269 |
--> |
| 270 |
<!-- [Facts & Implications Of The ISO Standard, as a reminder] |
| 271 |
- 'layout' is whitespace (space/tab/newline) and/or comments. |
| 272 |
- Braces (any of "(){}[]"), exclamation "!" (aka 'cut'), 'bar' "|", degree "°", |
| 273 |
paragraph "§" and percent "%" are NOT 'graphic' chars, but 'solo' chars. |
| 274 |
- The 'bar' "|" may be a predefined operator, and then a user-def'd op, too. |
| 275 |
- There can only be (at most) one bar "|" in a list (written inside "[]"), and |
| 276 |
no commata after it (after the bar). |
| 277 |
- Graphic tokens are atoms (and solo chars are one-char atoms?). |
| 278 |
- "{}" and "[]" are 'special atoms' (likewise "()"?). |
| 279 |
- "{}" and "[]" shall not be operators (but round or single braces may be?). |
| 280 |
- The fullstop "." is not a predefined postfix operator, and |
| 281 |
- the list functor "." is not a predefined prefix operator. |
| 282 |
- An unquoted graphic token shall not begin with "/*". |
| 283 |
- Multiline comments shall not be nested. |
| 284 |
- Floats are NOT written with lowercase "e" (i.e. not neccessarily an error if |
| 285 |
e.g. "e" is a pre- or user-defined expr or op and the whole term is valid), |
| 286 |
- and the fractional part and exponent of floats are optional (any and both). |
| 287 |
- A leading minus immediately preceding a number is optional for all numbers |
| 288 |
and then part of the number and not a prefix operator (currently beeing |
| 289 |
clarified by the standard commitee if "immediately" includes layout, only |
| 290 |
comments, or none of these at all ;) but |
| 291 |
- the minus "-" is a predefined prefix- and infix operator... |
| 292 |
- Terms are rewritten when read in, extendable by user-def'd rules (and these |
| 293 |
may be dynamic), i.e. clauses are not restricted to the standard forms |
| 294 |
(to the extent that the fullstop ending a clause may be omited at all) and |
| 295 |
- the dot "." may be (solo or part of) an user-defined operator. |
| 296 |
- A Prolog processor may use any character set, e.g. (multi-byte) Unicode. |
| 297 |
- Virtually every token may be an (user- or predefined) operator, except a few |
| 298 |
specifically excluded tokens (i.e. NOT just graphic and 'standard' atoms). |
| 299 |
- All operators except the comma are dynamic (although the standard denotes |
| 300 |
atoms as 'constants' ;), and |
| 301 |
- (the comma may appear in a user-defined operator (beeing part of it)?). |
| 302 |
(Now try to write syntax highlighting for Prolog w/o Prolog HAHAHA ;) |
| 303 |
--> |
| 304 |
<highlighting> |
| 305 |
<!-- aka "guru meditation trigger" --> |
| 306 |
<list name="error term ISO"> |
| 307 |
<item>error</item> |
| 308 |
</list> |
| 309 |
<list name="guru meditation terms ISO"> |
| 310 |
<item>instantiation_error</item> |
| 311 |
<item>uninstantiation_error</item> |
| 312 |
<item>type_error</item> |
| 313 |
<item>domain_error</item> |
| 314 |
<item>existence_error</item> |
| 315 |
<item>permission_error</item> |
| 316 |
<item>representation_error</item> |
| 317 |
<item>evaluation_error</item> |
| 318 |
<item>resource_error</item> |
| 319 |
<item>syntax_error</item> |
| 320 |
<item>system_error</item> |
| 321 |
</list> |
| 322 |
|
| 323 |
<!-- These are in fact bogus, DO NOT USE them and bug the ISO standard |
| 324 |
commitee to abandon char_conversion/2 and to apply common sense to the |
| 325 |
semantics of include/1 and ensure_loaded/1, i.e. to handle recursion. |
| 326 |
Bomb them w/ e-mails! It's not the purpose of a standard to fixate |
| 327 |
errors till eternity. --> |
| 328 |
<list name="bogus ISO"> |
| 329 |
<item>char_conversion</item> |
| 330 |
<item>current_char_conversion</item> |
| 331 |
<item>include</item> |
| 332 |
<item>ensure_loaded</item> |
| 333 |
<!-- Use atan2 instead --> |
| 334 |
<item>atan</item> |
| 335 |
<!-- Unspecified integer representation/format --> |
| 336 |
<item>xor</item> |
| 337 |
</list> |
| 338 |
<!-- including directive "initialization" --> |
| 339 |
<list name="logic+control ISO"> |
| 340 |
<item>initialization</item> |
| 341 |
<!-- <item>!</item> --> |
| 342 |
<item>fail</item> |
| 343 |
<item>repeat</item> |
| 344 |
<item>call</item> |
| 345 |
<item>catch</item> |
| 346 |
<item>throw</item> |
| 347 |
<item>true</item> |
| 348 |
<item>false</item> |
| 349 |
<item>once</item> |
| 350 |
</list> |
| 351 |
|
| 352 |
<!-- including directive "dynamic" --> |
| 353 |
<list name="dyn clause mgmt ISO"> |
| 354 |
<item>dynamic</item> |
| 355 |
<item>asserta</item> |
| 356 |
<item>assertz</item> |
| 357 |
<item>retractall</item> |
| 358 |
<item>retract</item> |
| 359 |
<item>abolish</item> |
| 360 |
<item>clause</item> |
| 361 |
<!-- <item>numbervars</item> --> |
| 362 |
<!-- <item>current_predicate</item> --> |
| 363 |
</list> |
| 364 |
<list name="terms ISO"> |
| 365 |
<!-- keep tokens with same prefix sorted by length? --> |
| 366 |
<item>atom_concat</item> |
| 367 |
<item>atom_length</item> |
| 368 |
<item>atom_chars</item> |
| 369 |
<item>atom_codes</item> |
| 370 |
<item>arg</item> |
| 371 |
<item>subsumes_term</item> |
| 372 |
<item>acyclic_term</item> |
| 373 |
<item>char_code</item> |
| 374 |
<item>compare</item> |
| 375 |
<item>copy_term</item> |
| 376 |
<item>functor</item> |
| 377 |
<item>number_chars</item> |
| 378 |
<item>number_codes</item> |
| 379 |
<!--FIXME check if GNU or ISO <item>sub_atom</item> --> |
| 380 |
<item>term_variables</item> |
| 381 |
<item>unify_with_occurs_check</item> |
| 382 |
</list> |
| 383 |
<list name="DCG non-ISO"> |
| 384 |
<item>phrase</item> |
| 385 |
</list> |
| 386 |
<list name="streams ISO"> |
| 387 |
<item>open</item> |
| 388 |
<!--GNU <item>current_stream</item>--> |
| 389 |
<item>set_stream_position</item> |
| 390 |
<item>get_char</item> |
| 391 |
<item>get_code</item> |
| 392 |
<item>peek_char</item> |
| 393 |
<item>peek_code</item> |
| 394 |
<item>get_byte</item> |
| 395 |
<item>peek_byte</item> |
| 396 |
|
| 397 |
<item>put_char</item> |
| 398 |
<item>put_code</item> |
| 399 |
<item>put_byte</item> |
| 400 |
<item>nl</item> |
| 401 |
|
| 402 |
<item>read_term</item> |
| 403 |
<item>read</item> |
| 404 |
<item>write_canonical</item> |
| 405 |
<item>writeq</item> |
| 406 |
<item>write</item> |
| 407 |
</list> |
| 408 |
<list name="arith eval ISO"> |
| 409 |
<item>is</item> |
| 410 |
</list> |
| 411 |
<list name="arith ops int ISO"> |
| 412 |
<item>rem</item> |
| 413 |
<item>mod</item> |
| 414 |
<item>div</item> |
| 415 |
</list> |
| 416 |
<list name="arith expr mixed ISO"> |
| 417 |
<!--GNU arith IF expr <item>inc</item> --> |
| 418 |
<!--GNU arith IF expr <item>dec</item> --> |
| 419 |
<item>abs</item> |
| 420 |
<item>sign</item> |
| 421 |
<item>min</item> |
| 422 |
<item>max</item> |
| 423 |
</list> |
| 424 |
<list name="arith expr int ISO"> |
| 425 |
<!--GNU arith IF expr <item>inc</item> --> |
| 426 |
<!--GNU arith IF expr <item>dec</item> --> |
| 427 |
<item>ceiling</item> |
| 428 |
<item>floor</item> |
| 429 |
<item>round</item> |
| 430 |
<item>truncate</item> |
| 431 |
<!-- ISO Bogus <item>xor</item> --> |
| 432 |
</list> |
| 433 |
<list name="arith expr float ISO"> |
| 434 |
<item>pi</item> |
| 435 |
<!--GNU (see pi) <item>e</item> --> |
| 436 |
<!--GNU (see pi) <item>epsilon</item> --> |
| 437 |
<item>sqrt</item> |
| 438 |
<item>tan</item> |
| 439 |
<item>cos</item> |
| 440 |
<item>sin</item> |
| 441 |
<item>atan2</item> |
| 442 |
<item>acos</item> |
| 443 |
<item>asin</item> |
| 444 |
<item>exp</item> |
| 445 |
<item>log</item> |
| 446 |
<item>float</item> |
| 447 |
<item>float_fractional_part</item> |
| 448 |
<item>float_integer_part</item> |
| 449 |
</list> |
| 450 |
|
| 451 |
<!-- including directives "op/multifile/discontigous" --> |
| 452 |
<list name="prolog state ISO"> |
| 453 |
<item>multifile</item> |
| 454 |
<item>discontigous</item> |
| 455 |
<item>op</item> |
| 456 |
<item>set_prolog_flag</item> |
| 457 |
</list> |
| 458 |
<list name="types ISO"> |
| 459 |
<item>var</item> |
| 460 |
<item>nonvar</item> |
| 461 |
<item>atom</item> |
| 462 |
<item>integer</item> |
| 463 |
<item>float</item> |
| 464 |
<item>number</item> |
| 465 |
<item>atomic</item> |
| 466 |
<item>compound</item> |
| 467 |
<item>callable</item> |
| 468 |
<item>ground</item> |
| 469 |
</list> |
| 470 |
<list name="built-ins ISO"> |
| 471 |
<item>current_op</item> |
| 472 |
<item>current_prolog_flag</item> |
| 473 |
<item>current_input</item> |
| 474 |
<item>current_output</item> |
| 475 |
|
| 476 |
<!-- These act on streams, but the permission_error is only thrown |
| 477 |
if the programmer tries to set_input(S) when S is alread an output |
| 478 |
stream and vice versa; so: not affected by 'outside world' --> |
| 479 |
<item>set_input</item> |
| 480 |
<item>set_output</item> |
| 481 |
|
| 482 |
<!-- may throw a system_error in GNU --> |
| 483 |
<item>close</item> |
| 484 |
|
| 485 |
<item>flush_output</item> |
| 486 |
|
| 487 |
<!-- may throw permission_error in GNU if S is an output stream --> |
| 488 |
<item>at_end_of_stream</item> |
| 489 |
|
| 490 |
<item>stream_property</item> |
| 491 |
</list> |
| 492 |
|
| 493 |
<!-- !FOLD the <context> rules & comments for an overview, then it's no magic. --> |
| 494 |
<contexts> |
| 495 |
<!-- Catch typos: style="Syntax Error" for all rules except comments and |
| 496 |
quoted. This helps to catch bugs in the rules itself, too. Nice |
| 497 |
debuging aid. Note that (naturally) some of the syntax rules given in |
| 498 |
EBNF are simplified and do not describe 100% valid Prolog. |
| 499 |
|
| 500 |
prolog text := shebang clause_seq | clause_seq |
| 501 |
clause_seq := clause clause_seq | empty |
| 502 |
clause := layout term_seq fullstop | term_seq fullstop |
| 503 |
--> |
| 504 |
<!-- shebang: ("#!") Detect shebang and fallthrough to clause_seq --> |
| 505 |
<context name="shebang" lineEndContext="clause" lineEmptyContext="clause" attribute="Syntax Error" fallthroughContext="clause"> |
| 506 |
<!-- no way: fallthroughContext="clause_seq" > --> |
| 507 |
<Detect2Chars column="0" char="#" char1="!" context="1-comment" attribute="% italic predicates: w/ side effects" /> |
| 508 |
<!-- else fallthrough (workaround broken fallthrough) --> |
| 509 |
</context> |
| 510 |
|
| 511 |
<!-- syntax error (Test & Debug Aid, too): it's enough to highlight next token --> |
| 512 |
<context name="syntax_error" lineEndContext="#stay" attribute="Syntax Error" noIndentationBasedFolding="true" > |
| 513 |
<DetectSpaces context="#pop" attribute="Syntax Error" /> |
| 514 |
<DetectIdentifier context="#pop" attribute="Syntax Error" /> |
| 515 |
<RegExpr String="&any;" context="#pop" attribute="Syntax Error" /> |
| 516 |
</context> |
| 517 |
|
| 518 |
<!-- clause: Start a region for code folding and switch to term --> |
| 519 |
<!-- <context name="clause" lineEndContext="#stay" attribute="Syntax Error" noIndentationBasedFolding="true" > --> |
| 520 |
<context name="clause" lineEndContext="#stay" attribute="Syntax Error" > |
| 521 |
<IncludeRules context="layout" /> |
| 522 |
<!-- KISS: do not force term to detect an empty clause as syntax error --> |
| 523 |
<RegExpr String="&fullstop_iso;" context="#stay" attribute="Warning (!use background)" /> |
| 524 |
<!-- <RegExpr lookAhead="true" String="&any;" context="term" attribute="Syntax Error" /> --> |
| 525 |
<RegExpr lookAhead="true" String="&any;" context="term" beginRegion="clause" attribute="Syntax Error" /> |
| 526 |
</context> |
| 527 |
|
| 528 |
<!--term/nested/list/curly: the master/dispatcher --> |
| 529 |
<!-- (abbreviated): term := var | atomic | compound | "(" term ")" |
| 530 |
|
| 531 |
(term_seq := term "," term_seq | term Not needed: comma is an op) |
| 532 |
term := layout solo layout | layout solo | solo layout | solo |
| 533 |
solo := var | atomic | compound | "(" term ")" |
| 534 |
compound := op term | term op | term op term | functored | list |
| 535 |
functored := atom "(" arg_seq ")" | op "(" arg_seq ")" |
| 536 |
list := "[" l_arg_seq "]" | double_quoted | "." "(" arg_seq ")" |
| 537 |
(if semantics of double_quoted not changed by set_prolog_flag/2) |
| 538 |
sorry I forgot curly: the DCG term but can not contain the fullstop. |
| 539 |
|
| 540 |
Comments in 'term' apply to the others as well. |
| 541 |
Note that eating layout once is enough, since we come back here. |
| 542 |
Only end the clause in the outmost term, which can only be term. --> |
| 543 |
<context name="term" lineEndContext="#stay" attribute="Syntax Error" noIndentationBasedFolding="true" > |
| 544 |
<IncludeRules context="layout" /> |
| 545 |
<DetectChar char="(" context="nested" beginRegion="nested" attribute="( ) [ ]" /> |
| 546 |
<DetectChar char="[" context="list" beginRegion="list" attribute="( ) [ ]" /> |
| 547 |
<DetectChar char="{" context="curly" beginRegion="curly" attribute="{ DCG }" /> |
| 548 |
<AnyChar String=",&cut;" context="#stay" attribute="Logic & Control" /> |
| 549 |
<DetectChar char="&bar;" context="#stay" attribute="Normal Text" /> |
| 550 |
<!-- lookAhead to give different style to the dot and the brace --> |
| 551 |
<Detect2Chars lookAhead="true" char="˙" char1="(" context="list_functor" attribute="Syntax Error" /> |
| 552 |
<!-- <RegExpr String="&fullstop_iso;" context="#pop" attribute="Logic & Control" /> --> |
| 553 |
<RegExpr String="&fullstop_iso;" context="#pop" endRegion="clause" attribute="Logic & Control" /> |
| 554 |
<IncludeRules context="atomic" /> |
| 555 |
<!-- Default: anything not eaten here is a syntax error --> |
| 556 |
</context> |
| 557 |
<context name="nested" lineEndContext="#stay" attribute="Syntax Error" noIndentationBasedFolding="true" > |
| 558 |
<IncludeRules context="layout" /> |
| 559 |
<DetectChar char=")" context="#pop" endRegion="nested" attribute="( ) [ ]" /> |
| 560 |
<DetectChar char="(" context="nested" beginRegion="nested" attribute="( ) [ ]" /> |
| 561 |
<DetectChar char="[" context="list" beginRegion="list" attribute="( ) [ ]" /> |
| 562 |
<DetectChar char="{" context="curly" beginRegion="curly" attribute="{ DCG }" /> |
| 563 |
<AnyChar String="&cut;," context="#stay" attribute="Logic & Control" /> |
| 564 |
<DetectChar char="&bar;" context="#stay" attribute="Normal Text" /> |
| 565 |
<Detect2Chars lookAhead="true" char="˙" char1="(" context="list_functor" attribute="Normal Text" /> |
| 566 |
<RegExpr String="&fullstop_iso;" context="#stay" attribute="Warning (!use background)" /> |
| 567 |
<IncludeRules context="atomic" /> |
| 568 |
</context> |
| 569 |
<context name="list" lineEndContext="#stay" attribute="Syntax Error" noIndentationBasedFolding="true" > |
| 570 |
<IncludeRules context="layout" /> |
| 571 |
<DetectChar char="(" context="nested" beginRegion="nested" attribute="( ) [ ]" /> |
| 572 |
<DetectChar char="]" context="#pop" endRegion="list" attribute="( ) [ ]" /> |
| 573 |
<DetectChar char="[" context="list" beginRegion="list" attribute="( ) [ ]" /> |
| 574 |
<DetectChar char="{" context="curly" beginRegion="curly" attribute="( ) [ ]" /> |
| 575 |
<AnyChar String=",&cut;" context="#stay" attribute="Normal Text" /> |
| 576 |
<DetectChar char="&bar;" context="#stay" attribute="other built-in operator" /> |
| 577 |
<Detect2Chars lookAhead="true" char="˙" char1="(" context="list_functor" attribute="Normal Text" /> |
| 578 |
<IncludeRules context="atomic" /> |
| 579 |
</context> |
| 580 |
<context name="curly" lineEndContext="#stay" attribute="Syntax Error" noIndentationBasedFolding="true" > |
| 581 |
<IncludeRules context="layout" /> |
| 582 |
<DetectChar char="(" context="nested" beginRegion="nested" attribute="( ) [ ]" /> |
| 583 |
<DetectChar char="[" context="list" beginRegion="list" attribute="( ) [ ]" /> |
| 584 |
<DetectChar char="}" context="#pop" endRegion="curly" attribute="{ DCG }" /> |
| 585 |
<DetectChar char="{" context="curly" beginRegion="curly" attribute="{ DCG }" /> |
| 586 |
<AnyChar String=",&cut;" context="#stay" attribute="Logic & Control" /> |
| 587 |
<DetectChar char="&bar;" context="#stay" attribute="Normal Text" /> |
| 588 |
<Detect2Chars lookAhead="true" char="˙" char1="(" context="list_functor" attribute="Normal Text" /> |
| 589 |
<IncludeRules context="atomic" /> |
| 590 |
</context> |
| 591 |
|
| 592 |
<!-- arith_expr := expr op expr | op expr | expr op | "(" expr ")" |
| 593 |
expr := number_expr | var | arith_expr |
| 594 |
|
| 595 |
This is only a goody to highlight arith ops and detect syntax errors. |
| 596 |
If it causes problems, disable it: exchange context="arith_expr" in |
| 597 |
"atomic" and "operator" below with context="#stay" (two or three occurrences) --> |
| 598 |
<context name="arith_expr" lineEndContext="#stay" attribute="Syntax Error" noIndentationBasedFolding="true" > |
| 599 |
<DetectChar char="(" context="nested_expr" beginRegion="nested" attribute="( ) [ ]" /> |
| 600 |
<!-- FIXME check if cut may be an op, else (and in any case 99.9% likely) it's a usual cut here --> |
| 601 |
<!-- bar & dot could be a user-def'd op, pre-def'd ops could be |
| 602 |
redef'd; but let's assume the default and just end the expr --> |
| 603 |
<AnyChar lookAhead="true" String=")}]&bar;&cut;,&bar;" context="#pop"/> |
| 604 |
<RegExpr lookAhead="true" String="&fullstop_iso;|&logic_control_ops_iso;" context="#pop" attribute="Logic & Control" /> |
| 605 |
<IncludeRules context="arith_expr_common" /> |
| 606 |
</context> |
| 607 |
<context name="nested_expr" lineEndContext="#stay" attribute="Syntax Error" noIndentationBasedFolding="true" > |
| 608 |
<DetectChar char="(" context="nested_expr" beginRegion="nested" attribute="( ) [ ]" /> |
| 609 |
<DetectChar char=")" context="#pop" endRegion="nested" attribute="( ) [ ]" /> |
| 610 |
<!-- FIXME check if cut may be an op, else it's a syntax error here --> |
| 611 |
<DetectChar char="&cut;" context="#stay" attribute="Normal Text" /> |
| 612 |
<DetectChar char="," context="#stay" attribute="Syntax Error" /> |
| 613 |
<!-- bar & dot could be a user-def'd op, pre-def'd ops could be redef'd; else these were errors --> |
| 614 |
<DetectChar char="&bar;" context="#stay" attribute="Normal Text" /> |
| 615 |
<RegExpr String="&logic_control_ops_iso;" context="#stay" attribute="other built-in operator" /> |
| 616 |
<IncludeRules context="arith_expr_common" /> |
| 617 |
</context> |
| 618 |
|
| 619 |
<!-- list functor: assign style to the dot and let term/list/curly take the brace |
| 620 |
(We have no style "built-in term", so take "Normal text" or "built-in predicate") |
| 621 |
ASSERT 1st is the dot, else "Syntax Error" INTENTIONALLY --> |
| 622 |
<context name="list_functor" lineEndContext="syntax_error" attribute="Syntax Error" > |
| 623 |
<DetectChar char="˙" context="#pop" attribute="other built-in predicate" /> |
| 624 |
</context> |
| 625 |
|
| 626 |
<!-- single/double/back-quoted: handle esc seq and closing quote |
| 627 |
Comments in single-quoted apply to the others as well. |
| 628 |
Entry point is single/double/back-quoted (only to handle syntax error: |
| 629 |
nl after opening quote), sq/dq/bq is inside the string. |
| 630 |
lineEndContext should be "syntax_error", but then we couldn't handle |
| 631 |
a valid esc'd line continuation. So we do that 'in vitro' (took me |
| 632 |
2 days w/ a plethora of useless rules to solve that puzzle LOL). |
| 633 |
On error must not #stay, else the error isn't shown iff white or empty --> |
| 634 |
<context name="sq" lineEndContext="#stay" attribute="'quo Ted'" noIndentationBasedFolding="true"> |
| 635 |
<!-- <context name="single-quoted" lineEndContext="#stay" attribute="'quo Ted'" > --> |
| 636 |
<IncludeRules context="quoted_1st"/> |
| 637 |
<!-- un-esc'd nl is a syntax error; match max seq (+), else the |
| 638 |
error is only shown in the next line --> |
| 639 |
<RegExpr String="(''|&esc_oct_iso;|&esc_hex_iso;|\\&any;|[^'\\]+)$" |
| 640 |
context="syntax_error_sq" attribute="Syntax Error" /> |
| 641 |
<!-- Usual handling: --> |
| 642 |
<Detect2Chars char="'" char1="'" context="#stay" attribute="escaped (!use background)" /> |
| 643 |
<DetectChar char="'" context="#pop#pop" endRegion="quoted" attribute="'quo Ted'" /> |
| 644 |
<IncludeRules context="quoted_last"/> |
| 645 |
<!-- Default: literal content of the quoted string, context's style applies --> |
| 646 |
</context> |
| 647 |
<context name="dq" lineEndContext="#stay" attribute=""double-quoted"" noIndentationBasedFolding="true" > |
| 648 |
<!-- <context name="double-quoted" lineEndContext="#stay" attribute=""double-quoted"" > --> |
| 649 |
<IncludeRules context="quoted_1st"/> |
| 650 |
<RegExpr String="(""|&esc_oct_iso;|&esc_hex_iso;|\\&any;|[^"\\]+)$" |
| 651 |
context="syntax_error_dq" attribute="Syntax Error" /> |
| 652 |
<Detect2Chars char=""" char1=""" context="#stay" attribute="escaped (!use background)" /> |
| 653 |
<DetectChar char=""" context="#pop#pop" endRegion="quoted" attribute=""double-quoted"" /> |
| 654 |
<IncludeRules context="quoted_last"/> |
| 655 |
</context> |
| 656 |
<context name="bq" lineEndContext="#stay" attribute="`back-quoted`" noIndentationBasedFolding="true" > |
| 657 |
<!-- <context name="back-quoted" lineEndContext="#stay" attribute="`back-quoted`" > --> |
| 658 |
<IncludeRules context="quoted_1st"/> |
| 659 |
<RegExpr String="(``|&esc_oct_iso;|&esc_hex_iso;|\\&any;|[^`\\]+)$" |
| 660 |
context="syntax_error_bq" attribute="Syntax Error" /> |
| 661 |
<Detect2Chars char="`" char1="`" attribute="escaped (!use background)" /> |
| 662 |
<DetectChar char="`" context="#pop#pop" endRegion="quoted" attribute="`back-quoted`" /> |
| 663 |
<IncludeRules context="quoted_last"/> |
| 664 |
</context> |
| 665 |
<context name="single-quoted" lineEndContext="#stay" attribute="'quo Ted'" > |
| 666 |
<LineContinue char="'" context="sq" beginRegion="quoted" attribute="Syntax Error" /> |
| 667 |
<DetectChar char="'" context="sq" beginRegion="quoted" attribute="'quo Ted'" /> |
| 668 |
</context> |
| 669 |
<context name="double-quoted" lineEndContext="#stay" attribute=""double-quoted"" > |
| 670 |
<LineContinue char=""" context="dq" beginRegion="quoted" attribute="Syntax Error" /> |
| 671 |
<DetectChar char=""" context="dq" beginRegion="quoted" attribute=""double-quoted"" /> |
| 672 |
</context> |
| 673 |
<context name="back-quoted" lineEndContext="#stay" attribute="`back-quoted`" > |
| 674 |
<LineContinue char="`" context="bq" beginRegion="quoted" attribute="Syntax Error" /> |
| 675 |
<DetectChar char="`" context="bq" beginRegion="quoted" attribute="`back-quoted`" /> |
| 676 |
</context> |
| 677 |
|
| 678 |
<!-- syntax_error_q: highlight next token and proceed normal afterwards --> |
| 679 |
<context name="syntax_error_sq" lineEndContext="#stay" attribute="Syntax Error" noIndentationBasedFolding="true" > |
| 680 |
<Detect2Chars char="\" char1="'" context="#pop" attribute="Syntax Error" /> |
| 681 |
<Detect2Chars char="'" char1="'" context="#pop" attribute="Syntax Error" /> |
| 682 |
<DetectChar char="'" context="#pop#pop#pop" endRegion="quoted" attribute="Syntax Error" /> |
| 683 |
<IncludeRules context="syntax_error"/> |
| 684 |
</context> |
| 685 |
<context name="syntax_error_dq" lineEndContext="#stay" attribute="Syntax Error" noIndentationBasedFolding="true" > |
| 686 |
<Detect2Chars char="\" char1=""" context="#pop" attribute="Syntax Error" /> |
| 687 |
<Detect2Chars char=""" char1=""" context="#pop" attribute="Syntax Error" /> |
| 688 |
<DetectChar char=""" context="#pop#pop#pop" endRegion="quoted" attribute="Syntax Error" /> |
| 689 |
<IncludeRules context="syntax_error"/> |
| 690 |
</context> |
| 691 |
<context name="syntax_error_bq" lineEndContext="#stay" attribute="Syntax Error" noIndentationBasedFolding="true" > |
| 692 |
<Detect2Chars char="\" char1="`" context="#pop" attribute="Syntax Error" /> |
| 693 |
<Detect2Chars char="`" char1="`" context="#pop" attribute="Syntax Error" /> |
| 694 |
<DetectChar char="`" context="#pop#pop#pop" endRegion="quoted" attribute="Syntax Error" /> |
| 695 |
<IncludeRules context="syntax_error"/> |
| 696 |
</context> |
| 697 |
|
| 698 |
<!-- char_code (after "0'"): esc seq, singleq twice, or any other --> |
| 699 |
<context name="char_code" lineEndContext="#pop" attribute="Syntax Error" > |
| 700 |
<Detect2Chars char="'" char1="'" context="#pop" attribute="escaped (!use background)" /> |
| 701 |
<DetectChar char="'" context="#pop" attribute="Syntax Error" /> |
| 702 |
<DetectChar char="&bs;" context="esc_seq_cc" attribute="escaped (!use background)" /> |
| 703 |
<DetectChar char="&tab;" context="#pop" attribute="Warning (!use background)" /> |
| 704 |
<!-- Default _AND IF_ esc_seq #pops back here; we need this to #pop out --> |
| 705 |
<RegExpr String="&any;" context="#pop" attribute="0'a (!use background)" /> |
| 706 |
</context> |
| 707 |
<!-- "0'" or "0'\" at EOL is a syntax error, catched below. If |
| 708 |
possible, highlight white @next line to make clear error is the nl --> |
| 709 |
<context name="syntax_error_cc" lineEndContext="#stay" attribute="Syntax Error" |
| 710 |
fallthroughContext="#pop" > |
| 711 |
<DetectSpaces context="#pop" attribute="Syntax Error" /> |
| 712 |
</context> |
| 713 |
|
| 714 |
<!-- esc_seq: it's not worth it to handle common for quoted and cc |
| 715 |
esc_seq_q: handle only cc in bs (e.g. "\007\"), else -> esc_seq_q2 |
| 716 |
ASSERT esc'd newline is handled by the calling context |
| 717 |
ASSERT we get the leading bs here to highlight the whole thing --> |
| 718 |
<context name="esc_seq_q" lineEndContext="syntax_error" attribute="Syntax Error" > |
| 719 |
<RegExpr String="&esc_oct_iso;|&esc_hex_iso;" context="#pop" attribute="0'a (!use background)" /> |
| 720 |
<DetectChar char="&bs;" context="esc_seq_q2" attribute="escaped (!use background)" /> |
| 721 |
</context> |
| 722 |
<!-- esc_seq_cc: #pop#pop out of cc on std esc seq, else pass char back |
| 723 |
ASSERT we do NOT need the leading bs here anymore --> |
| 724 |
<context name="esc_seq_cc" fallthroughContext="#pop" |
| 725 |
lineEndContext="#pop#pop" attribute="Syntax Error" > |
| 726 |
<DetectChar char="&tab;" context="#pop#pop" attribute="Warning (!use background)" /> |
| 727 |
<AnyChar String="&any_esc_iso;" context="#pop#pop" attribute="escaped (!use background)" /> |
| 728 |
</context> |
| 729 |
<!-- esc_seq_q2: Handle standard esc seq in quoted else pass char back |
| 730 |
ASSERT we do NOT need the leading bs here anymore --> |
| 731 |
<context name="esc_seq_q2" fallthroughContext="#pop#pop" |
| 732 |
lineEndContext="syntax_error" attribute="Syntax Error" > |
| 733 |
<DetectChar char="&tab;" context="#pop#pop" attribute="Warning (!use background)" /> |
| 734 |
<AnyChar String="&any_esc_iso;" context="#pop#pop" attribute="escaped (!use background)" /> |
| 735 |
</context> |
| 736 |
|
| 737 |
<!-- id,var,graphic: ASSERT calling context ashured 1st char is ok |
| 738 |
ASSERT we get the 1st char for id & var --> |
| 739 |
<context name="id" attribute="Syntax Error" lineEndContext="#stay" > |
| 740 |
<DetectIdentifier context="#pop" attribute="Normal Text" /> |
| 741 |
</context> |
| 742 |
<context name="var" attribute="Syntax Error" lineEndContext="#stay" > |
| 743 |
<DetectIdentifier context="#pop" attribute="_VARIABLE" /> |
| 744 |
</context> |
| 745 |
<context name="graphic" lineEndContext="#pop" attribute="Syntax Error" fallthroughContext="#pop" > |
| 746 |
<AnyChar String="&any_graphic_iso;" context="#stay" attribute="Normal Text" /> |
| 747 |
</context> |
| 748 |
|
| 749 |
<!-- numbers (after "0[box]") --> |
| 750 |
<context name="bin" lineEndContext="#pop" attribute="Syntax Error" fallthroughContext="#pop" > |
| 751 |
<AnyChar String="&any_bin_iso;" context="#stay" attribute="0b1001 0o007 0xF1" /> |
| 752 |
</context> |
| 753 |
<context name="oct" lineEndContext="#pop" attribute="Syntax Error" fallthroughContext="#pop" > |
| 754 |
<AnyChar String="&any_oct_iso;" context="#stay" attribute="0b1001 0o007 0xF1" /> |
| 755 |
</context> |
| 756 |
<context name="hex" lineEndContext="#pop" attribute="Syntax Error" fallthroughContext="#pop" > |
| 757 |
<AnyChar String="&any_hex_iso;" context="#stay" attribute="0b1001 0o007 0xF1" /> |
| 758 |
</context> |
| 759 |
|
| 760 |
<!-- comment-iso: multi-line comment, handle closing "*/" --> |
| 761 |
<context name="comment-iso" lineEndContext="#stay" attribute="% italic predicates: w/ side effects" > |
| 762 |
<!-- Nested comments are not allowed in strict ISO-Prolog - - > |
| 763 |
<Detect2Chars char="/" char1="*" context="comment" beginRegion="comment" |
| 764 |
attribute="% italic predicates: w/ side effects" />--> |
| 765 |
<Detect2Chars char="*" char1="/" context="#pop" endRegion="comment" |
| 766 |
attribute="% italic predicates: w/ side effects" /> |
| 767 |
<DetectSpaces /> |
| 768 |
<IncludeRules context="##Comments" /> |
| 769 |
<DetectIdentifier /> |
| 770 |
</context> |
| 771 |
|
| 772 |
<!-- 1-line comment: #pop@EOL --> |
| 773 |
<!-- Folding for consecutive 1-line comments: let indentation-based auto-folding work --> |
| 774 |
<context name="1-comment" lineEndContext="#pop" attribute="% italic predicates: w/ side effects" > |
| 775 |
<DetectSpaces /> |
| 776 |
<IncludeRules context="##Comments" /> |
| 777 |
<DetectIdentifier /> |
| 778 |
</context> |
| 779 |
<context name="region_marker" lineEndContext="#pop" attribute="%BEGIN folding region" noIndentationBasedFolding="true" > |
| 780 |
<IncludeRules context="1-comment" /> |
| 781 |
</context> |
| 782 |
<context name="layout_fold" lineEndContext="#stay" attribute="Syntax Error" |
| 783 |
fallthroughContext="#pop" > |
| 784 |
<DetectSpaces attribute="Normal Text" /> |
| 785 |
<StringDetect String="%BEGIN" context="region_marker" attribute="%BEGIN folding region" |
| 786 |
firstNonSpace="true" beginRegion="user_region" /> |
| 787 |
<StringDetect String="%END" context="region_marker" attribute="%BEGIN folding region" |
| 788 |
firstNonSpace="true" endRegion="user_region" /> |
| 789 |
<DetectChar firstNonSpace="true" char="%" context="1-comment" attribute="% italic predicates: w/ side effects" /> |
| 790 |
</context> |
| 791 |
|
| 792 |
<!--####### BEGIN sub rules to be included - <context> never taken --> |
| 793 |
|
| 794 |
<!-- Common for all quoted: Handle line continuation, esc seq, and most other input efficiently --> |
| 795 |
<context name="quoted_1st" lineEndContext="#stay" attribute="Syntax Error" > |
| 796 |
<LineContinue attribute="escaped (!use background)" /> |
| 797 |
<DetectSpaces column="0" attribute="escaped (!use background)" /> |
| 798 |
</context> |
| 799 |
<context name="quoted_last" lineEndContext="#stay" attribute="Syntax Error" > |
| 800 |
<DetectChar lookAhead="true" char="&bs;" context="esc_seq_q" attribute="Syntax Error" /> |
| 801 |
<DetectChar char="&tab;" attribute="Warning (!use background)" /> |
| 802 |
<DetectIdentifier /> |
| 803 |
<DetectSpaces /> |
| 804 |
</context> |
| 805 |
|
| 806 |
<!-- layout_seq := layout layout_seq |
| 807 |
layout := " " | tab | nl | comment --> |
| 808 |
<context name="layout" lineEndContext="#stay" attribute="Syntax Error" > |
| 809 |
<DetectSpaces attribute="Normal Text" /> |
| 810 |
<Detect2Chars char="/" char1="*" context="comment-iso" attribute="% italic predicates: w/ side effects" |
| 811 |
beginRegion="comment" /> |
| 812 |
<StringDetect String="%BEGIN" context="region_marker" attribute="%BEGIN folding region" |
| 813 |
firstNonSpace="true" beginRegion="user_region" /> |
| 814 |
<StringDetect String="%END" context="region_marker" attribute="%BEGIN folding region" |
| 815 |
firstNonSpace="true" endRegion="user_region" /> |
| 816 |
<DetectChar firstNonSpace="true" char="%" context="layout_fold" attribute="% italic predicates: w/ side effects" |
| 817 |
lookAhead="true" /> |
| 818 |
<DetectChar firstNonSpace="false" char="%" context="1-comment" attribute="% italic predicates: w/ side effects" /> |
| 819 |
</context> |
| 820 |
|
| 821 |
<!--atomic: the work horse --> |
| 822 |
<!-- (simplified) atomic := atom | number | op | var --> |
| 823 |
<context name="atomic" lineEndContext="#stay" attribute="Syntax Error" > |
| 824 |
<!-- NOTE the order of rules is important... (as always) |
| 825 |
Predefined 1st, unknown (user defined) last --> |
| 826 |
<keyword String="logic+control ISO" context="#stay" attribute="Logic & Control" /> |
| 827 |
<keyword String="types ISO" context="#stay" attribute="Type Checking" /> |
| 828 |
<keyword String="dyn clause mgmt ISO" context="#stay" attribute="Dynamic Clause Management" /> |
| 829 |
<keyword String="streams ISO" context="#stay" attribute="Stream I/O" /> |
| 830 |
<keyword String="terms ISO" context="#stay" attribute="other built-in predicate" /> |
| 831 |
<keyword String="prolog state ISO" context="#stay" attribute="Prolog State" /> |
| 832 |
<keyword String="DCG non-ISO" context="#stay" attribute="{ DCG }" /> |
| 833 |
<keyword String="arith eval ISO" context="arith_expr" attribute="Arithmetics" /> |
| 834 |
<!-- These are user predicates outside arit_expr --> |
| 835 |
<!-- <keyword String="arith expr mixed ISO" context="#stay" attribute="other built-in predicate" /> --> |
| 836 |
<!-- <keyword String="arith expr int ISO" context="#stay" attribute="other built-in predicate" /> --> |
| 837 |
<!-- <keyword String="arith expr float ISO" context="#stay" attribute="other built-in predicate" /> --> |
| 838 |
<keyword String="built-ins ISO" context="#stay" attribute="other built-in predicate" /> |
| 839 |
<keyword String="error term ISO" context="#stay" attribute="Guru Meditation" /> |
| 840 |
<keyword String="guru meditation terms ISO" context="#stay" attribute="Guru Meditation Terms" /> |
| 841 |
<keyword String="bogus ISO" context="#stay" attribute="ISO Bogus" /> |
| 842 |
|
| 843 |
<!-- Match char code before quoted and ops... --> |
| 844 |
<IncludeRules context="number" /> |
| 845 |
|
| 846 |
<!-- these depend on current_prolog_flag/2 so can all return a term i.e. a list (of char codes) --> |
| 847 |
<DetectChar lookAhead="true" char="'" context="single-quoted" attribute="'quo Ted'" /> |
| 848 |
<DetectChar lookAhead="true" char="`" context="back-quoted" attribute="`back-quoted`" /> |
| 849 |
<DetectChar lookAhead="true" char=""" context="double-quoted" attribute=""double-quoted"" /> |
| 850 |
|
| 851 |
<!-- ...and ops before atoms, else "div", "is" etc. are usual atoms --> |
| 852 |
<IncludeRules context="operator" /> |
| 853 |
<AnyChar lookAhead="true" String="&any_lower_iso;" context="id" attribute="Normal Text" /> |
| 854 |
<AnyChar lookAhead="true" String="&any_upper_under_iso;" context="var" attribute="_VARIABLE" /> |
| 855 |
<AnyChar String="&any_graphic_iso;" context="graphic" attribute="Normal Text" /> |
| 856 |
</context> <!-- atomic --> |
| 857 |
|
| 858 |
<!-- [(mostly) "atomic" for] arith_expr := arith_op | number_expr | var |
| 859 |
number_expr := number | built-in | user-def |
| 860 |
|
| 861 |
This is only a goody to highlight arith ops and detect syntax errors. |
| 862 |
If it causes problems, disable it: exchange context="arith_expr" in |
| 863 |
contexts "atomic" and "operator" with context="#stay" --> |
| 864 |
<context name="arith_expr_common" lineEndContext="#stay" attribute="Syntax Error" > |
| 865 |
<IncludeRules context="layout" /> |
| 866 |
<IncludeRules context="number" /> |
| 867 |
<keyword String="bogus ISO" context="#stay" attribute="ISO Bogus" /> |
| 868 |
<keyword String="arith expr mixed ISO" context="#stay" attribute="Arithmetics" /> |
| 869 |
<keyword String="arith expr int ISO" context="#stay" attribute="Integer Arithmetics" /> |
| 870 |
<keyword String="arith expr float ISO" context="#stay" attribute="Float Arithmetics" /> |
| 871 |
<keyword String="arith ops int ISO" context="#stay" attribute="Integer Arithmetics" /> |
| 872 |
<RegExpr String="&arith_compare_iso;" context="#pop" attribute="Syntax Error" /> |
| 873 |
<RegExpr String="&arith_ops_mixed_iso;" context="#stay" attribute="Arithmetics" /> |
| 874 |
<RegExpr String="&arith_ops_int_iso;" context="#stay" attribute="Integer Arithmetics" /> |
| 875 |
<RegExpr String="&arith_ops_float_iso;" context="#stay" attribute="Float Arithmetics" /> |
| 876 |
<RegExpr String="&arith_bogus_iso;" context="#stay" attribute="ISO Bogus" /> |
| 877 |
<!-- do not miss user-def'd arithmetic expr and number expr--> |
| 878 |
<IncludeRules context="operator" /> |
| 879 |
<AnyChar lookAhead="true" String="&any_lower_iso;" context="id" attribute="Normal Text" /> |
| 880 |
<AnyChar lookAhead="true" String="&any_upper_under_iso;" context="var" attribute="_VARIABLE" /> |
| 881 |
<AnyChar String="&any_graphic_iso;" context="graphic" attribute="Normal Text" /> |
| 882 |
</context> |
| 883 |
|
| 884 |
<!-- number := float | integer |
| 885 |
integer := decimal | baseN | "0'" char_code |
| 886 |
baseN := "0b" [01]+ | "0o" [0-7]+ | "0x" [0-9a-fA-F]+ --> |
| 887 |
<context name="number" lineEndContext="#pop" attribute="Syntax Error" > |
| 888 |
<!-- Match integers after other numbers --> |
| 889 |
<!-- FIXME a minus may precede all numbers and is part of the number! --> |
| 890 |
<RegExpr String="0'\\?$" context="syntax_error_cc" attribute="Syntax Error" /> |
| 891 |
<Detect2Chars char="0" char1="'" context="char_code" attribute="0'a (!use background)" /> |
| 892 |
|
| 893 |
<!-- NOT: [box] could be a postfix op <RegExpr String="0[box]$" context="#stay" attribute="Syntax Error" /> --> |
| 894 |
<Detect2Chars char="0" char1="b" context="bin" attribute="0b1001 0o007 0xF1" /> |
| 895 |
<Detect2Chars char="0" char1="o" context="oct" attribute="0b1001 0o007 0xF1" /> |
| 896 |
<Detect2Chars char="0" char1="x" context="hex" attribute="0b1001 0o007 0xF1" /> |
| 897 |
|
| 898 |
<RegExpr String="&float1_iso;|&float2_iso;|&float3_iso;" context="#stay" attribute="2.718281E-9" /> |
| 899 |
<Int context="#stay" attribute="1 2 3 42" /> |
| 900 |
</context> |
| 901 |
|
| 902 |
<!-- operator := predefined_op | dynamic_op (which we can not detect) |
| 903 |
comma, single dot & bar are catched earlier above in term/list/curly --> |
| 904 |
<context name="operator" lineEndContext="#pop" attribute="Syntax Error" > |
| 905 |
<keyword String="arith eval ISO" context="arith_expr" attribute="Arithmetics" /> |
| 906 |
<keyword String="arith ops int ISO" context="#stay" attribute="other built-in operator" /> |
| 907 |
<RegExpr String="&logic_control_ops_iso;" context="#stay" attribute="Logic & Control" /> |
| 908 |
<RegExpr String="&predefined_ops_iso;" context="#stay" attribute="other built-in operator" /> |
| 909 |
<RegExpr String="&dcg_production_iso;" context="#stay" attribute="{ DCG }" /> |
| 910 |
<RegExpr String="&arith_compare_iso;" context="arith_expr" attribute="Arithmetics" /> |
| 911 |
<RegExpr String="&arith_ops_mixed_iso;|&arith_ops_int_iso;|&arith_ops_float_iso;" context="#stay" attribute="other built-in operator" /> |
| 912 |
<RegExpr String="&arith_bogus_iso;" context="#stay" attribute="ISO Bogus" /> |
| 913 |
</context> |
| 914 |
|
| 915 |
<!--####### END sub rules to be included - <context> never taken --> |
| 916 |
</contexts> |
| 917 |
|
| 918 |
<!-- The idea is to give all predicates that may be affected by the |
| 919 |
"outside world" a common style (italic). I.e. these can throw a |
| 920 |
permission, evaluation, representation or resource_error, even though |
| 921 |
the program itself is 100% correct. E.g. you get_char/2 a char code 1 |
| 922 |
from a text stream (representation_error): not your mistake, but you |
| 923 |
have to deal with that, too. --> |
| 924 |
<itemDatas> |
| 925 |
<itemData name="Normal Text" defStyleNum="dsNormal" spellChecking="false" /> |
| 926 |
<itemData name="_VARIABLE" defStyleNum="dsDataType" bold="false" spellChecking="false" /> |
| 927 |
<itemData name="'quo Ted'" defStyleNum="dsString" /> |
| 928 |
<itemData name="`back-quoted`" defStyleNum="dsString" italic="true" /> |
| 929 |
<!-- The standard wants double-quoted to be a list of char codes, but |
| 930 |
e.g. GNU Prolog allows that to be set with set_prolog_flag/2 --> |
| 931 |
<itemData name=""double-quoted"" defStyleNum="dsOthers" /> |
| 932 |
<itemData name="escaped (!use background)" defStyleNum="dsChar" spellChecking="false" |
| 933 |
backgroundColor="#0C0C0C" selBackgroundColor="#FFFFFF" /> |
| 934 |
|
| 935 |
<!-- Numbers --> |
| 936 |
<itemData name="2.718281E-9" defStyleNum="dsFloat" spellChecking="false" /> |
| 937 |
<itemData name="1 2 3 42" defStyleNum="dsDecVal" spellChecking="false" /> |
| 938 |
<itemData name="0b1001 0o007 0xF1" defStyleNum="dsBaseN" spellChecking="false" /> |
| 939 |
<itemData name="0'a (!use background)" defStyleNum="dsBaseN" spellChecking="false" |
| 940 |
backgroundColor="#0C0C0C" selBackgroundColor="#FFFFFF" /> |
| 941 |
|
| 942 |
<itemData name="( ) [ ]" defStyleNum="dsNormal" spellChecking="false" /> |
| 943 |
<itemData name="{ DCG }" defStyleNum="dsKeyword" spellChecking="false" /> |
| 944 |
<itemData name="Prolog State" defStyleNum="dsFunction" bold="true" spellChecking="false" /> |
| 945 |
<itemData name="Type Checking" defStyleNum="dsDataType" spellChecking="false" /> |
| 946 |
<itemData name="Logic & Control" defStyleNum="dsKeyword" spellChecking="false" /> |
| 947 |
<itemData name="other built-in operator" defStyleNum="dsFunction" spellChecking="false" /> |
| 948 |
<itemData name="other built-in predicate" defStyleNum="dsFunction" spellChecking="false" /> |
| 949 |
|
| 950 |
<!-- Comments (2nd not used, just a hint) --> |
| 951 |
<itemData name="% italic predicates: w/ side effects" defStyleNum="dsComment" /> |
| 952 |
|
| 953 |
<!-- Predicates affected by 'outside world' --> |
| 954 |
<itemData name="Dynamic Clause Management" defStyleNum="dsKeyword" italic="true" spellChecking="false" /> |
| 955 |
<itemData name="Stream I/O" defStyleNum="dsFunction" italic="true" spellChecking="false" /> |
| 956 |
|
| 957 |
<!-- arithmetics: get the color of ints/floats; includes ops & expressions like pi --> |
| 958 |
<itemData name="Arithmetics" defStyleNum="dsDataType" bold="true" italic="true" spellChecking="false" /> |
| 959 |
<itemData name="Integer Arithmetics" defStyleNum="dsDecVal" bold="true" italic="true" spellChecking="false" /> |
| 960 |
<itemData name="Float Arithmetics" defStyleNum="dsFloat" bold="true" italic="true" spellChecking="false" /> |
| 961 |
<itemData name="ISO Bogus" defStyleNum="dsAlert" bold="true" italic="true" spellChecking="false" /> |
| 962 |
|
| 963 |
<!-- no way w/ buggy kate 3.8.5: get the color of default style dsError for error and terms --> |
| 964 |
<itemData name="Guru Meditation" defStyleNum="dsNormal" spellChecking="false" |
| 965 |
bold="true" italic="false" underline="false" color="#FF0000" selColor="#00FFFF" /> |
| 966 |
<itemData name="Guru Meditation Terms" defStyleNum="dsNormal" spellChecking="false" |
| 967 |
bold="false" italic="true" underline="false" color="#FF0000" selColor="#00FFFF" /> |
| 968 |
<itemData name="Syntax Error" defStyleNum="dsError" spellChecking="false" /> |
| 969 |
<itemData name="Warning (!use background)" defStyleNum="dsAlert" spellChecking="false" |
| 970 |
backgroundColor="#FC000C" selBackgroundColor="#03FFF3" /> |
| 971 |
<itemData name="%BEGIN folding region" defStyleNum="dsRegionMarker" spellChecking="false" /> |
| 972 |
</itemDatas> |
| 973 |
</highlighting> |
| 974 |
<general> |
| 975 |
<keywords casesensitive="true" additionalDeliminator="$#'"`" /> |
| 976 |
<!-- let indentationsensitive folding provide it's magic --> |
| 977 |
<folding indentationsensitive="true" /> |
| 978 |
<!-- <EmptyLines> --> |
| 979 |
<!-- <EmptyLine regexpr="^[ /t]*(?!%).*$" /> --> |
| 980 |
<!-- </EmptyLines> --> |
| 981 |
<comments> |
| 982 |
<comment name="singleLine" start="%" position="afterwhitespace" /> |
| 983 |
<comment name="multiLine" start="/*" end="*/" region="comment" /> |
| 984 |
</comments> |
| 985 |
</general> |
| 986 |
</language> |
| 987 |
<!--##### NOTE [HOWTO check your syntax file, extracted from language.dtd] ##### |
| 988 |
|
| 989 |
Copyright (c) 2001 Joseph Wenninger <[email protected]> |
| 990 |
modified (c) 2002 Anders Lund <[email protected]> |
| 991 |
modified (c) 2003 Simon Huerlimann <[email protected]> |
| 992 |
modified (c) 2005 Dominik Haumann <[email protected]> |
| 993 |
modified (c) 2008 Wilbert Berendsen <[email protected]> |
| 994 |
|
| 995 |
You can validate your syntax files using checkXML from the development |
| 996 |
package of kdelibs [author: i.e. kdelibs-dev]: |
| 997 |
|
| 998 |
checkXML yourSyntax.xml [author: | grep -v 'no template matches'] |
| 999 |
|
| 1000 |
If you see any 'validity error' lines, you should fix them. If you get |
| 1001 |
a lot of 'No template matches' lines, everything's just fine. You've |
| 1002 |
produced a valid syntax file! |
| 1003 |
|
| 1004 |
It's also possible to use the (much faster) xmllint which comes with the |
| 1005 |
GNOME (oops:-) XML Library libxml2: |
| 1006 |
|
| 1007 |
xmllint - -dtdvalid language.dtd yourSyntax.xml |
| 1008 |
(don't use a space between the two - [author: dashes/minus] |
| 1009 |
That's just because XML comments don't allow that:-( |
| 1010 |
|
| 1011 |
To use your syntax file, copy it to .kde/share/apps/katepart/syntax/ in |
| 1012 |
your home directory. You have to open a new instance of kwrite/kate to use |
| 1013 |
the new syntax file. |
| 1014 |
--> |
| 1015 |
<!-- kate: replace-tabs off; --> |