Skip to content
Snippets Groups Projects
check_style_c.py 36.9 KiB
Newer Older
  • Learn to ignore specific revisions
  • 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000
    #!/usr/bin/env python3
    
    # ***** BEGIN GPL LICENSE BLOCK *****
    #
    # This program 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 2
    # of the License, or (at your option) any later version.
    #
    # This program 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 this program; if not, write to the Free Software Foundation,
    # Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
    #
    # Contributor(s): Campbell Barton
    #
    # #**** END GPL LICENSE BLOCK #****
    
    # <pep8 compliant>
    
    """
    This script runs outside of blender and scans source
    
       python3 source/tools/check_source/check_source_c.py source/
    """
    
    import os
    
    from check_style_c_config import IGNORE, IGNORE_DIR, SOURCE_DIR
    IGNORE = tuple([os.path.join(SOURCE_DIR, ig) for ig in IGNORE])
    IGNORE_DIR = tuple([os.path.join(SOURCE_DIR, ig) for ig in IGNORE_DIR])
    WARN_TEXT = False
    
    
    def is_ignore(f):
        for ig in IGNORE:
            if f == ig:
                return True
        for ig in IGNORE_DIR:
            if f.startswith(ig):
                return True
        return False
    
    print("Scanning:", SOURCE_DIR)
    
    # TODO
    #
    # Add checks for:
    # - macro brace use
    # - line length - in a not-too-annoying way
    #   (allow for long arrays in struct definitions, PyMethodDef for eg)
    
    from pygments import lex  # highlight
    from pygments.lexers import CLexer
    from pygments.formatters import RawTokenFormatter
    
    from pygments.token import Token
    
    import argparse
    
    PRINT_QTC_TASKFORMAT = False
    if "USE_QTC_TASK" in os.environ:
        PRINT_QTC_TASKFORMAT = True
    
    TAB_SIZE = 4
    LIN_SIZE = 120
    
    global filepath
    tokens = []
    
    
    # could store index here too, then have prev/next methods
    class TokStore:
        __slots__ = ("type", "text", "line")
    
        def __init__(self, type, text, line):
            self.type = type
            self.text = text
            self.line = line
    
    
    def tk_range_to_str(a, b, expand_tabs=False):
        txt = "".join([tokens[i].text for i in range(a, b + 1)])
        if expand_tabs:
            txt = txt.expandtabs(TAB_SIZE)
        return txt
    
    
    def tk_item_is_newline(tok):
        return tok.type == Token.Text and tok.text.strip("\t ") == "\n"
    
    
    def tk_item_is_ws_newline(tok):
        return (tok.text == "") or \
               (tok.type == Token.Text and tok.text.isspace()) or \
               (tok.type in Token.Comment)
    
    
    def tk_item_is_ws(tok):
        return (tok.text == "") or \
               (tok.type == Token.Text and tok.text.strip("\t ") != "\n" and tok.text.isspace()) or \
               (tok.type in Token.Comment)
    
    
    # also skips comments
    def tk_advance_ws(index, direction):
        while tk_item_is_ws(tokens[index + direction]) and index > 0:
            index += direction
        return index
    
    
    def tk_advance_no_ws(index, direction):
        index += direction
        while tk_item_is_ws(tokens[index]) and index > 0:
            index += direction
        return index
    
    
    def tk_advance_ws_newline(index, direction):
        while tk_item_is_ws_newline(tokens[index + direction]) and index > 0:
            index += direction
        return index + direction
    
    
    def tk_advance_line_start(index):
        """ Go the the first non-whitespace token of the line.
        """
        while tokens[index].line == tokens[index - 1].line and index > 0:
            index -= 1
        return tk_advance_no_ws(index, 1)
    
    
    def tk_advance_line(index, direction):
        line = tokens[index].line
        while tokens[index + direction].line == line or tokens[index].text == "\n":
            index += direction
        return index
    
    
    def tk_match_backet(index):
        backet_start = tokens[index].text
        assert(tokens[index].type == Token.Punctuation)
        assert(backet_start in "[]{}()")
    
        if tokens[index].text in "({[":
            direction = 1
            backet_end = {"(": ")", "[": "]", "{": "}"}[backet_start]
        else:
            direction = -1
            backet_end = {")": "(", "]": "[", "}": "{"}[backet_start]
    
        level = 1
        index_match = index + direction
        while True:
            item = tokens[index_match]
            if item.type == Token.Punctuation:
                if item.text == backet_start:
                    level += 1
                elif item.text == backet_end:
                    level -= 1
                    if level == 0:
                        break
    
            index_match += direction
    
        return index_match
    
    
    def tk_index_is_linestart(index):
        index_prev = tk_advance_ws_newline(index, -1)
        return tokens[index_prev].line < tokens[index].line
    
    
    def extract_to_linestart(index):
        ls = []
        line = tokens[index].line
        index -= 1
        while index > 0 and tokens[index].line == line:
            ls.append(tokens[index].text)
            index -= 1
    
        if index != 0:
            ls.append(tokens[index].text.rsplit("\n", 1)[1])
    
        ls.reverse()
        return "".join(ls)
    
    
    def extract_statement_if(index_kw):
        # assert(tokens[index_kw].text == "if")
    
        # seek back
        i = index_kw
    
        i_start = tk_advance_ws(index_kw - 1, direction=-1)
    
        # seek forward
        i_next = tk_advance_ws_newline(index_kw, direction=1)
    
        # print(tokens[i_next])
    
        # ignore preprocessor
        i_linestart = tk_advance_line_start(index_kw)
        if tokens[i_linestart].text.startswith("#"):
            return None
    
        if tokens[i_next].type != Token.Punctuation or tokens[i_next].text != "(":
            warning("no '(' after '%s'" % tokens[index_kw].text, i_start, i_next)
            return None
    
        i_end = tk_match_backet(i_next)
    
        return (i_start, i_end)
    
    
    def extract_operator(index_op):
        op_text = ""
        i = 0
        while tokens[index_op + i].type == Token.Operator:
            op_text += tokens[index_op + i].text
            i += 1
        return op_text, index_op + (i - 1)
    
    
    def extract_cast(index):
        # to detect a cast is quite involved... sigh
        # assert(tokens[index].text == "(")
    
        # TODO, comment within cast, but thats rare
        i_start = index
        i_end = tk_match_backet(index)
    
        # first check we are not '()'
        if i_start + 1 == i_end:
            return None
    
        # check we have punctuation before the cast
        i = i_start - 1
        while tokens[i].text.isspace():
            i -= 1
        i_prev_no_ws = i
        if tokens[i].type in {Token.Keyword, Token.Name}:
            # avoids  'foo(bar)test'
            # but not ' = (bar)test'
            return None
    
        # validate types
        tokens_cast = [tokens[i] for i in range(i_start + 1, i_end)]
        for t in tokens_cast:
            if t.type == Token.Keyword:
                return None
            elif t.type == Token.Operator and t.text != "*":
                # prevent '(a + b)'
                # note, we could have '(float(*)[1+2])' but this is unlikely
                return None
            elif t.type == Token.Punctuation and t.text not in '()[]':
                # prevent '(a, b)'
                return None
        tokens_cast_strip = []
        for t in tokens_cast:
            if t.type in Token.Comment:
                pass
            elif t.type == Token.Text and t.text.isspace():
                pass
            else:
                tokens_cast_strip.append(t)
        # check token order and types
        if not tokens_cast_strip:
            return None
        if tokens_cast_strip[0].type not in {Token.Name, Token.Type, Token.Keyword.Type}:
            return None
        t_prev = None
        for t in tokens_cast_strip[1:]:
            # prevent identifiers after the first: '(a b)'
            if t.type in {Token.Keyword.Type, Token.Name, Token.Text}:
                return None
            # prevent: '(a * 4)'
            # allow:   '(a (*)[4])'
            if t_prev is not None and t_prev.text == "*" and t.type != Token.Punctuation:
                return None
            t_prev = t
        del t_prev
    
        # debug only
        '''
        string = "".join(tokens[i].text for i in range(i_start, i_end + 1))
        #string = "".join(tokens[i].text for i in range(i_start + 1, i_end))
        #types = [tokens[i].type for i in range(i_start + 1, i_end)]
        types = [t.type for t in tokens_cast_strip]
    
        print("STRING:", string)
        print("TYPES: ", types)
        print()
        '''
    
        return (i_start, i_end)
    
    
    def warning(message, index_kw_start, index_kw_end):
        if PRINT_QTC_TASKFORMAT:
            print("%s\t%d\t%s\t%s" % (filepath, tokens[index_kw_start].line, "comment", message))
        else:
            print("%s:%d: warning: %s" % (filepath, tokens[index_kw_start].line, message))
            if WARN_TEXT:
                print(tk_range_to_str(index_kw_start, index_kw_end, expand_tabs=True))
    
    
    def warning_lineonly(message, line):
        if PRINT_QTC_TASKFORMAT:
            print("%s\t%d\t%s\t%s" % (filepath, line, "comment", message))
        else:
            print("%s:%d: warning: %s" % (filepath, line, message))
    
        # print(tk_range_to_str(index_kw_start, index_kw_end))
    
    
    # ------------------------------------------------------------------
    # Own Blender rules here!
    
    def blender_check_kw_if(index_kw_start, index_kw, index_kw_end):
    
        # check if we have: 'if('
        if not tk_item_is_ws(tokens[index_kw + 1]):
            warning("no white space between '%s('" % tokens[index_kw].text, index_kw_start, index_kw_end)
    
        # check for: ){
        index_next = tk_advance_ws_newline(index_kw_end, 1)
        if tokens[index_next].type == Token.Punctuation and tokens[index_next].text == "{":
            if not tk_item_is_ws(tokens[index_next - 1]):
                warning("no white space between trailing bracket '%s (){'" % tokens[index_kw].text, index_kw_start, index_kw_end)
    
            # check for: if ()
            #            {
            # note: if the if statement is multi-line we allow it
            if     ((tokens[index_kw].line == tokens[index_kw_end].line) and
                    (tokens[index_kw].line == tokens[index_next].line - 1)):
    
                warning("if body brace on a new line '%s ()\\n{'" % tokens[index_kw].text, index_kw, index_kw_end)
        else:
            # no '{' on a multi-line if
            if tokens[index_kw].line != tokens[index_kw_end].line:
                warning("multi-line if should use a brace '%s (\\n\\n) statement;'" % tokens[index_kw].text, index_kw, index_kw_end)
    
        # check for: if (a &&
        #                b) { ...
        # brace should be on a newline.
        if (tokens[index_kw].line != tokens[index_kw_end].line):
            if tokens[index_kw_end].line == tokens[index_next].line:
                warning("multi-line should use a on a new line '%s (\\n\\n) {'" % tokens[index_kw].text, index_kw, index_kw_end)
    
        # check for: if () { ... };
        #
        # no need to have semicolon after brace.
        if tokens[index_next].text == "{":
            index_final = tk_match_backet(index_next)
            index_final_step = tk_advance_no_ws(index_final, 1)
            if tokens[index_final_step].text == ";":
                warning("semi-colon after brace '%s () { ... };'" % tokens[index_kw].text, index_final_step, index_final_step)
    
    
    def blender_check_kw_else(index_kw):
        # for 'else if' use the if check.
        i_next = tk_advance_ws_newline(index_kw, 1)
    
        # check there is at least one space between:
        # else{
        if index_kw + 1 == i_next:
            warning("else has no space between following brace 'else{'", index_kw, i_next)
    
        # check if there are more than 1 spaces after else, but nothing after the following brace
        # else     {
        #     ...
        #
        # check for this case since this is needed sometimes:
        # else     { a = 1; }
        if     ((tokens[index_kw].line == tokens[i_next].line) and
                (tokens[index_kw + 1].type == Token.Text) and
                (len(tokens[index_kw + 1].text) > 1) and
                (tokens[index_kw + 1].text.isspace())):
    
            # check if the next data after { is on a newline
            i_next_next = tk_advance_ws_newline(i_next, 1)
            if tokens[i_next].line != tokens[i_next_next].line:
                warning("unneeded whitespace before brace 'else ... {'", index_kw, i_next)
    
        # this check only tests for:
        # else
        # {
        # ... which is never OK
        #
        # ... except if you have
        # else
        # #preprocessor
        # {
    
        if tokens[i_next].type == Token.Punctuation and tokens[i_next].text == "{":
            if tokens[index_kw].line < tokens[i_next].line:
                # check for preproc
                i_newline = tk_advance_line(index_kw, 1)
                if tokens[i_newline].text.startswith("#"):
                    pass
                else:
                    warning("else body brace on a new line 'else\\n{'", index_kw, i_next)
    
        # this check only tests for:
        # else
        # if
        # ... which is never OK
        if tokens[i_next].type == Token.Keyword and tokens[i_next].text == "if":
            if tokens[index_kw].line < tokens[i_next].line:
                warning("else if is split by a new line 'else\\nif'", index_kw, i_next)
    
        # check
        # } else
        # ... which is never OK
        i_prev = tk_advance_no_ws(index_kw, -1)
        if tokens[i_prev].type == Token.Punctuation and tokens[i_prev].text == "}":
            if tokens[index_kw].line == tokens[i_prev].line:
                warning("else has no newline before the brace '} else'", i_prev, index_kw)
    
    
    def blender_check_kw_switch(index_kw_start, index_kw, index_kw_end):
        # In this function we check the body of the switch
    
        # switch (value) {
        # ...
        # }
    
        # assert(tokens[index_kw].text == "switch")
    
        index_next = tk_advance_ws_newline(index_kw_end, 1)
    
        if tokens[index_next].type == Token.Punctuation and tokens[index_next].text == "{":
            ws_switch_indent = extract_to_linestart(index_kw)
    
            if ws_switch_indent.isspace():
    
                # 'case' should have at least 1 indent.
                # otherwise expect 2 indent (or more, for nested switches)
                ws_test = {
                    "case": ws_switch_indent + "\t",
                    "default:": ws_switch_indent + "\t",
    
                    "break": ws_switch_indent + "\t\t",
                    "return": ws_switch_indent + "\t\t",
                    "continue": ws_switch_indent + "\t\t",
                    "goto": ws_switch_indent + "\t\t",
                    }
    
                index_final = tk_match_backet(index_next)
    
                case_ls = []
    
                for i in range(index_next + 1, index_final):
                    # 'default' is seen as a label
                    # print(tokens[i].type, tokens[i].text)
                    if tokens[i].type in {Token.Keyword, Token.Name.Label}:
                        if tokens[i].text in {"case", "default:", "break", "return", "comtinue", "goto"}:
                            ws_other_indent = extract_to_linestart(i)
                            # non ws start - we ignore for now, allow case A: case B: ...
                            if ws_other_indent.isspace():
                                ws_test_other = ws_test[tokens[i].text]
                                if not ws_other_indent.startswith(ws_test_other):
                                    warning("%s is not indented enough" % tokens[i].text, i, i)
    
                                # assumes correct indentation...
                                if tokens[i].text in {"case", "default:"}:
                                    if ws_other_indent == ws_test_other:
                                        case_ls.append(i)
    
                case_ls.append(index_final - 1)
    
                # detect correct use of break/return
                for j in range(len(case_ls) - 1):
                    i_case = case_ls[j]
                    i_end = case_ls[j + 1]
    
                    # detect cascading cases, check there is one line inbetween at least
                    if tokens[i_case].line + 1 < tokens[i_end].line:
                        ok = False
    
                        # scan case body backwards
                        for i in reversed(range(i_case, i_end)):
                            if tokens[i].type == Token.Punctuation:
                                if tokens[i].text == "}":
                                    ws_other_indent = extract_to_linestart(i)
                                    if ws_other_indent != ws_test["case"]:
                                        # break/return _not_ found
                                        break
    
                            elif tokens[i].type in Token.Comment:
                                if tokens[i].text == "/* fall-through */":
                                    ok = True
                                    break
                                else:
                                    #~ print("Commment '%s'" % tokens[i].text)
                                    pass
    
    
                            elif tokens[i].type == Token.Keyword:
                                if tokens[i].text in {"break", "return", "continue", "goto"}:
                                    if tokens[i_case].line == tokens[i].line:
                                        # Allow for...
                                        #     case BLAH: var = 1; break;
                                        # ... possible there is if statements etc, but assume not
                                        ok = True
                                        break
                                    else:
                                        ws_other_indent = extract_to_linestart(i)
                                        ws_other_indent = ws_other_indent[:len(ws_other_indent) - len(ws_other_indent.lstrip())]
                                        ws_test_other = ws_test[tokens[i].text]
                                        if ws_other_indent == ws_test_other:
                                            ok = True
                                            break
                                        else:
                                            pass
                                            #~ print("indent mismatch...")
                                            #~ print("'%s'" % ws_other_indent)
                                            #~ print("'%s'" % ws_test_other)
                        if not ok:
                            warning("case/default statement has no break", i_case, i_end)
                            #~ print(tk_range_to_str(i_case - 1, i_end - 1, expand_tabs=True))
            else:
                warning("switch isn't the first token in the line", index_kw_start, index_kw_end)
        else:
            warning("switch brace missing", index_kw_start, index_kw_end)
    
    
    def blender_check_kw_sizeof(index_kw):
        if tokens[index_kw + 1].text != "(":
            warning("expected '%s('" % tokens[index_kw].text, index_kw, index_kw + 1)
    
    
    def blender_check_cast(index_kw_start, index_kw_end):
        # detect: '( float...'
        if tokens[index_kw_start + 1].text.isspace():
            warning("cast has space after first bracket '( type...'", index_kw_start, index_kw_end)
        # detect: '...float )'
        if tokens[index_kw_end - 1].text.isspace():
            warning("cast has space before last bracket '... )'", index_kw_start, index_kw_end)
        # detect no space before operator: '(float*)'
    
        for i in range(index_kw_start + 1, index_kw_end):
            if tokens[i].text == "*":
                # allow: '(*)'
                if tokens[i - 1].type == Token.Punctuation:
                    pass
                elif tokens[i - 1].text.isspace():
                    pass
                else:
                    warning("cast has no preceeding whitespace '(type*)'", index_kw_start, index_kw_end)
    
    
    def blender_check_comma(index_kw):
        i_next = tk_advance_ws_newline(index_kw, 1)
    
        # check there is at least one space between:
        # ,sometext
        if index_kw + 1 == i_next:
            warning("comma has no space after it ',sometext'", index_kw, i_next)
    
        if tokens[index_kw - 1].type == Token.Text and tokens[index_kw - 1].text.isspace():
            warning("comma space before it 'sometext ,", index_kw, i_next)
    
    
    def blender_check_period(index_kw):
        # check we're now apart of ...
        if (tokens[index_kw - 1].text == ".") or (tokens[index_kw + 1].text == "."):
            return
    
        # 'a.b'
        if tokens[index_kw - 1].type == Token.Text and tokens[index_kw - 1].text.isspace():
            warning("period space before it 'sometext .", index_kw, index_kw)
        if tokens[index_kw + 1].type == Token.Text and tokens[index_kw + 1].text.isspace():
            warning("period space after it '. sometext", index_kw, index_kw)
    
    
    def _is_ws_pad(index_start, index_end):
        return (tokens[index_start - 1].text.isspace() and
                tokens[index_end + 1].text.isspace())
    
    
    def blender_check_operator(index_start, index_end, op_text, is_cpp):
        if op_text == "->":
            # allow compiler to handle
            return
    
        if len(op_text) == 1:
            if op_text in {"+", "-"}:
                # detect (-a) vs (a - b)
                if     (not tokens[index_start - 1].text.isspace() and
                        tokens[index_start - 1].text not in {"[", "(", "{"}):
                    warning("no space before operator '%s'" % op_text, index_start, index_end)
                if     (not tokens[index_end + 1].text.isspace() and
                        tokens[index_end + 1].text not in {"]", ")", "}"}):
                    # TODO, needs work to be useful
                    # warning("no space after operator '%s'" % op_text, index_start, index_end)
                    pass
    
            elif op_text in {"/", "%", "^", "|", "=", "<", ">"}:
                if not _is_ws_pad(index_start, index_end):
                    if not (is_cpp and ("<" in op_text or ">" in op_text)):
                        warning("no space around operator '%s'" % op_text, index_start, index_end)
            elif op_text == "&":
                pass  # TODO, check if this is a pointer reference or not
            elif op_text == "*":
               # This check could be improved, its a bit fuzzy
                if     ((tokens[index_start - 1].type in Token.Number) or
                        (tokens[index_start + 1].type in Token.Number)):
                    warning("no space around operator '%s'" % op_text, index_start, index_end)
                elif not (tokens[index_start - 1].text.isspace() or tokens[index_start - 1].text in {"(", "[", "{"}):
                    warning("no space before operator '%s'" % op_text, index_start, index_end)
        elif len(op_text) == 2:
            # todo, remove operator check from `if`
            if op_text in {"+=", "-=", "*=", "/=", "&=", "|=", "^=",
                           "&&", "||",
                           "==", "!=", "<=", ">=",
                           "<<", ">>",
                           "%=",
                           # not operators, pointer mix-ins
                           ">*", "<*", "-*", "+*", "=*", "/*", "%*", "^*", "|*",
                           }:
                if not _is_ws_pad(index_start, index_end):
                    if not (is_cpp and ("<" in op_text or ">" in op_text)):
                        warning("no space around operator '%s'" % op_text, index_start, index_end)
    
            elif op_text in {"++", "--"}:
                pass  # TODO, figure out the side we are adding to!
                '''
                if     (tokens[index_start - 1].text.isspace() or
                        tokens[index_end   + 1].text.isspace()):
                    warning("spaces surrounding operator '%s'" % op_text, index_start, index_end)
                '''
            elif op_text in {"!!", "!*"}:
                # operators we _dont_ want whitespace after (pointers mainly)
                # we can assume these are pointers
                if tokens[index_end + 1].text.isspace():
                    warning("spaces after operator '%s'" % op_text, index_start, index_end)
    
            elif op_text == "**":
                pass  # handle below
            elif op_text == "::":
                pass  # C++, ignore for now
            elif op_text == ":!*":
                pass  # ignore for now
            elif op_text == "*>":
                pass  # ignore for now, C++ <Class *>
            else:
                warning("unhandled operator A '%s'" % op_text, index_start, index_end)
        else:
            #warning("unhandled operator B '%s'" % op_text, index_start, index_end)
            pass
    
        if len(op_text) > 1:
            if op_text[0] == "*" and op_text[-1] == "*":
                if     ((not tokens[index_start - 1].text.isspace()) and
                        (not tokens[index_start - 1].type == Token.Punctuation)):
                    warning("no space before pointer operator '%s'" % op_text, index_start, index_end)
                if tokens[index_end + 1].text.isspace():
                    warning("space before pointer operator '%s'" % op_text, index_start, index_end)
    
        # check if we are first in the line
        if op_text[0] == "!":
            # if (a &&
            #     !b)
            pass
        elif op_text[0] == "*" and tokens[index_start + 1].text.isspace() is False:
            pass  # *a = b
        elif len(op_text) == 1 and op_text[0] == "-" and tokens[index_start + 1].text.isspace() is False:
            pass  # -1
        elif len(op_text) == 2 and op_text == "++" and tokens[index_start + 1].text.isspace() is False:
            pass  # ++a
        elif len(op_text) == 2 and op_text == "--" and tokens[index_start + 1].text.isspace() is False:
            pass  # --a
        elif len(op_text) == 1 and op_text[0] == "&":
            # if (a &&
            #     &b)
            pass
        elif len(op_text) == 1 and op_text[0] == "~":
            # C++
            # ~ClassName
            pass
        elif len(op_text) == 1 and op_text[0] == "?":
            # (a == b)
            # ? c : d
            pass
        elif len(op_text) == 1 and op_text[0] == ":":
            # a = b ? c
            #      : d
            pass
        else:
            if tk_index_is_linestart(index_start):
                warning("operator starts a new line '%s'" % op_text, index_start, index_end)
    
    
    def blender_check_linelength(index_start, index_end, length):
        if length > LIN_SIZE:
            text = tk_range_to_str(index_start, index_end, expand_tabs=True)
            for l in text.split("\n"):
                if len(l) > LIN_SIZE:
                    warning("line length %d > %d" % (len(l), LIN_SIZE), index_start, index_end)
    
    
    def blender_check_function_definition(i):
        # Warning, this is a fairly slow check and guesses
        # based on some fuzzy rules
    
        # assert(tokens[index].text == "{")
    
        # check function declaration is not:
        #  'void myfunc() {'
        # ... other uses are handled by checks for statements
        # this check is rather simplistic but tends to work well enough.
    
        i_prev = i - 1
        while tokens[i_prev].text == "":
            i_prev -= 1
    
        # ensure this isnt '{' in its own line
        if tokens[i_prev].line == tokens[i].line:
    
            # check we '}' isnt on same line...
            i_next = i + 1
            found = False
            while tokens[i_next].line == tokens[i].line:
                if tokens[i_next].text == "}":
                    found = True
                    break
                i_next += 1
            del i_next
    
            if found is False:
    
                # First check this isnt an assignment
                i_prev = tk_advance_no_ws(i, -1)
                # avoid '= {'
                #if tokens(index_prev).text != "="
                # print(tokens[i_prev].text)
                # allow:
                # - 'func()[] {'
                # - 'func() {'
    
                if tokens[i_prev].text in {")", "]"}:
                    i_prev = i - 1
                    while tokens[i_prev].line == tokens[i].line:
                        i_prev -= 1
                    split = tokens[i_prev].text.rsplit("\n", 1)
                    if len(split) > 1 and split[-1] != "":
                        split_line = split[-1]
                    else:
                        split_line = tokens[i_prev + 1].text
    
                    if split_line and split_line[0].isspace():
                        pass
                    else:
                        # no whitespace!
                        i_begin = i_prev + 1
    
                        # skip blank
                        if tokens[i_begin].text == "":
                            i_begin += 1
                        # skip static
                        if tokens[i_begin].text == "static":
                            i_begin += 1
                        while tokens[i_begin].text.isspace():
                            i_begin += 1
                        # now we are done skipping stuff
    
                        warning("function's '{' must be on a newline", i_begin, i)
    
    
    def blender_check_brace_indent(i):
        # assert(tokens[index].text == "{")
    
        i_match = tk_match_backet(i)
    
        if tokens[i].line != tokens[i_match].line:
            ws_i_match = extract_to_linestart(i_match)
    
            # allow for...
            # a[] = {1, 2,
            #        3, 4}
            # ... so only check braces which are the first text
            if ws_i_match.isspace():
                ws_i = extract_to_linestart(i)
                ws_i_match_lstrip = ws_i_match.lstrip()
    
                ws_i = ws_i[:len(ws_i) - len(ws_i.lstrip())]
                ws_i_match = ws_i_match[:len(ws_i_match) - len(ws_i_match_lstrip)]
                if ws_i != ws_i_match:
                    warning("indentation '{' does not match brace", i, i_match)
    
    
    def quick_check_indentation(lines):
        """
        Quick check for multiple tab indents.
        """
        t_prev = -1
        m_comment_prev = False
        ls_prev = ""
    
        for i, l in enumerate(lines):
            skip = False
    
            # skip blank lines
            ls = l.strip()
    
            # comment or pre-processor
            if ls:
                # #ifdef ... or ... // comment
                if (ls[0] == "#" or ls[0:2] == "//"):
                    skip = True
                # label:
                elif (':' in ls and l[0] != '\t'):
                    skip = True
                # /* comment */
                #~ elif ls.startswith("/*") and ls.endswith("*/"):
                #~     skip = True
                # /* some comment...
                elif ls.startswith("/*"):
                    skip = True
                # line ending a comment: */
                elif ls == "*/":
                    skip = True
                # * middle of multi line comment block
                elif ls.startswith("* "):
                    skip = True
                # exclude muli-line defines
                elif ls.endswith("\\") or ls.endswith("(void)0") or ls_prev.endswith("\\"):
                    skip = True
    
            ls_prev = ls
    
            if skip:
                continue
    
            if ls:
                ls = l.lstrip("\t")
                tabs = l[:len(l) - len(ls)]
                t = len(tabs)
                if (t > t_prev + 1) and (t_prev != -1):
                    warning_lineonly("indentation mis-match (indent of %d) '%s'" % (t - t_prev, tabs), i + 1)
                t_prev = t
    
    import re
    re_ifndef = re.compile("^\s*#\s*ifndef\s+([A-z0-9_]+).*$")
    re_define = re.compile("^\s*#\s*define\s+([A-z0-9_]+).*$")
    
    def quick_check_include_guard(lines):
        found = 0
        def_value = ""
        ok = False
    
        def fn_as_guard(fn):
            name = os.path.basename(fn).upper().replace(".", "_").replace("-", "_")
            return "__%s__" % name
    
        for i, l in enumerate(lines):
            ndef_match = re_ifndef.match(l)
            if ndef_match:
                ndef_value = ndef_match.group(1).strip()
                for j in range(i + 1, len(lines)):
                    l_next = lines[j]
                    def_match = re_define.match(l_next)
                    if def_match:
                        def_value = def_match.group(1).strip()
                        if def_value == ndef_value:
                            ok = True
                            break
                    elif l_next.strip():
                        # print(filepath)
                        # found non empty non ndef line. quit
                        break
                    else:
                        # allow blank lines
                        pass
                break
    
        guard = fn_as_guard(filepath)
    
        if ok:
            # print("found:", def_value, "->", filepath)
            if def_value != guard:
                # print("%s: %s -> %s" % (filepath, def_value, guard))
                warning_lineonly("non-conforming include guard (found %r, expected %r)" % (def_value, guard), i + 1)
        else:
            warning_lineonly("missing include guard %r" % guard, 1)
    
    def quick_check_source(fp, code, args):
    
        global filepath
    
        is_header = fp.endswith((".h", ".hxx", ".hpp"))
    
        filepath = fp
    
        lines = code.split("\n")
    
        if is_header:
            quick_check_include_guard(lines)
    
        quick_check_indentation(lines)
    
    def scan_source(fp, code, args):
        # print("scanning: %r" % fp)
    
        global filepath
    
        is_cpp = fp.endswith((".cpp", ".cxx"))
    
        filepath = fp
    
        #if "displist.c" not in filepath:
        #    return
    
        filepath_base = os.path.basename(filepath)
    
        #print(highlight(code, CLexer(), RawTokenFormatter()).decode('utf-8'))
    
        del tokens[:]
        line = 1
    
        for ttype, text in lex(code, CLexer()):
            if text:
                tokens.append(TokStore(ttype, text, line))
                line += text.count("\n")
    
        col = 0  # track line length
        index_line_start = 0
    
        for i, tok in enumerate(tokens):
            #print(tok.type, tok.text)
            if tok.type == Token.Keyword:
                if tok.text in {"switch", "while", "if", "for"}:
                    item_range = extract_statement_if(i)
                    if item_range is not None:
                        blender_check_kw_if(item_range[0], i, item_range[1])
                    if tok.text == "switch":
                        blender_check_kw_switch(item_range[0], i, item_range[1])
                elif tok.text == "else":
                    blender_check_kw_else(i)
                elif tok.text == "sizeof":
                    blender_check_kw_sizeof(i)
            elif tok.type == Token.Punctuation:
                if tok.text == ",":
                    blender_check_comma(i)
                elif tok.text == ".":
                    blender_check_period(i)
                elif tok.text == "[":
                    # note, we're quite relaxed about this but
                    # disallow 'foo ['
                    if tokens[i - 1].text.isspace():
                        if is_cpp and tokens[i + 1].text == "]":
                            # c++ can do delete []
                            pass
                        else:
                            warning("space before '['", i, i)
                elif tok.text == "(":
                    # check if this is a cast, eg:
                    #  (char), (char **), (float (*)[3])
                    item_range = extract_cast(i)
                    if item_range is not None:
                        blender_check_cast(item_range[0], item_range[1])
                elif tok.text == "{":
                    # check matching brace is indented correctly (slow!)
                    blender_check_brace_indent(i)
    
                    # check previous character is either a '{' or whitespace.
                    if (tokens[i - 1].line == tok.line) and not (tokens[i - 1].text.isspace() or tokens[i - 1].text == "{"):
                        warning("no space before '{'", i, i)
    
                    blender_check_function_definition(i)
    
            elif tok.type == Token.Operator:
                # we check these in pairs, only want first
                if tokens[i - 1].type != Token.Operator:
                    op, index_kw_end = extract_operator(i)
                    blender_check_operator(i, index_kw_end, op, is_cpp)
            elif tok.type in Token.Comment:
                doxyfn = None
                if "\\file" in tok.text:
                    doxyfn = tok.text.split("\\file", 1)[1].strip().split()[0]
                elif "@file" in tok.text:
                    doxyfn = tok.text.split("@file", 1)[1].strip().split()[0]
    
                if doxyfn is not None:
                    doxyfn_base = os.path.basename(doxyfn)
                    if doxyfn_base != filepath_base:
                        warning("doxygen filename mismatch %s != %s" % (doxyfn_base, filepath_base), i, i)
    
            # ensure line length
            if (not args.no_length_check) and tok.type == Token.Text and tok.text == "\n":
                # check line len
                blender_check_linelength(index_line_start, i - 1, col)
    
                col = 0